Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds a real operational constraint not present in the schema — that only aprx_path=CURRENT is accepted — and clarifies the response is 'real-time' view/camera data. It does not discuss failure modes when no view is active.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One compact sentence with the resource description front-loaded and the aprx_path constraint trailing; no filler text at all.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description covers what is read plus the key parameter constraint. It is nearly complete for a simple read tool, missing only what happens when no active view exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter meaning, and it does: it pins aprx_path to the single accepted value CURRENT. That is genuinely valuable beyond the bare string-typed schema, though no format example or rationale is given.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (读取/read) and resource (当前窗口的活动地图/布局视图和实时相机范围), so an agent knows it returns the current window's active view plus camera extent. It does not explicitly differentiate itself from look-alike siblings such as arcgis_pro_map_camera or arcgis_pro_window_status, keeping it below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause '仅支持 aprx_path=CURRENT' gives an important precondition for use, implying this only works against the currently open project. However, it never says when to prefer this over siblings like map_camera or sdk_context, so usage is only implied rather than routed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is covered. The description adds one piece of real behavioral context — that paths are bound by an input root policy — which is not derivable from annotations. It still omits what happens on partial failure or whether existing attachments are replaced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the operative behaviour first and the constraint after; no filler. It is efficient, though arguably too terse for a six-parameter mutation tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but for a six-parameter destructive-adjacent mutation with 0% parameter coverage the description is far too thin. The agent cannot determine how to populate the join fields or what a failed batch means.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there are 6 parameters (5 required), yet the description only loosely gestures at 'match table' and 'path'. The critical join semantics — in_join_field, match_join_field, match_path_field, dataset_path — are undocumented in both description and schema, so the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource+method: '批量添加附件' (batch add attachments) via a '匹配表' (match table). This clearly distinguishes it from sibling attachment tools like remove_attachments or attachments_info. It stops short of explicitly naming a sibling, so it is a clear purpose without sibling routing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of the other attachment tools (attachments_info, enable_attachments, disable_attachments, remove_attachments) that an agent must choose between. The agent is left to infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is partly covered. The description adds genuinely new behavioral context – that changes are gated, post-verified ('后验核验'), and require a confirmation phrase and precise target echo – but these terms are compressed and not fully explained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with semicolons that front-loads the core action (creating the rule) before the constraints. No filler, though the compression makes some clauses hard to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 18-parameter destructive mutation with an output schema present, the description is minimal – it names the gating/confirmation behavior but gives no coverage of the many configuration parameters (rule_type, triggering_events, subtypes, severity, etc.). Adequate but leaves significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 18 parameters and 0% schema description coverage, the description carries the full burden of explaining parameters, yet it only obliquely references two of them ('目标精确回显' for expected_dataset and '固定确认短语' for confirmation). The other 16 parameters receive no semantic help at all.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('创建受约束属性规则' – create constrained attribute rules) and names the underlying official operation (AddAttributeRule). It is distinguishable from siblings like delete/list/export/import_attribute_rules, though '受约束' (constrained) is left undefined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It hints at invocation prerequisites – '方案变更双门' (dual gate for schema change) and '固定确认短语' (fixed confirmation phrase) – which implies this is a gated mutation, but it never states when to prefer this over siblings such as import_attribute_rules or list_attribute_rules. Usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the mutation profile is partly covered. The description's only behavioral content is boilerplate ("returns verifiable structured results; write and path restrictions subject to service capabilities"), which does not say what gets modified, whether the aprx must be saved, or what path constraints actually apply. It does not contradict the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the two sentences are generic boilerplate that could be pasted onto any tool in this server, so neither earns its place. The front-loaded content is a restatement of the name rather than useful scoping information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, but for a mutating tool with three undocumented parameters and no sibling differentiation the description leaves the agent without the essentials. It does not cover prerequisites, the target map/aprx relationship, or valid basemap names.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema documents none of the three required parameters, and the description adds nothing about map_name, aprx_path, or basemap_name — not even whether basemap_name must match an entry from arcgis_pro_list_basemaps. The description fails to compensate for the complete absence of parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description essentially restates the tool name and title ("ArcGIS Pro: Add add basemap") with a redundant bilingual repetition, so it reads as a tautology. It never distinguishes this tool from siblings such as arcgis_pro_list_basemaps or arcgis_pro_add_layer_from_path, so an agent cannot tell which basemap-adjacent operation this is without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool, what prerequisites it needs (an open project, a target map), or when to prefer an alternative. The only vaguely directive phrase, "write and path restrictions subject to service capabilities," does not tell the agent anything actionable about invocation conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, which already tells the agent this is a non-destructive, non-idempotent write. The description adds nothing further: it does not say the domain must already exist, whether the workspace is a geodatabase path, whether duplicate codes are rejected or overwritten, or whether changes persist immediately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with no wasted words and a front-loaded verb. It is concise but under-specified rather than well-structured; there is no additional sentence to earn its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but for a mutation tool with four required params, zero schema coverage and no annotations beyond generic hints, the description leaves critical operational context (target workspace, domain preconditions, duplicate handling) missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there are 4 required parameters. The description only implicitly references 'code' and 'description' and says nothing about workspace_path or domain_name, leaving half the required inputs unexplained in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource pair (add a code/description to a coded value domain) and is clearly distinguishable from siblings like delete_coded_value_from_domain. However, it offers no explicit sibling differentiation or scope qualifiers beyond the name/title restatement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as alter_domain or delete_coded_value_from_domain. The agent must infer everything from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true, idempotent=false, openWorld=false. The description adds genuinely useful behavior beyond that: verification that only a unique new item is created, a dual-gate scheme change requirement, exact target echo, and a fixed confirmation phrase. These are meaningful operational constraints not present in the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the action front-loaded and the constraints trailing; no filler. Slightly compressed for a tool with this many preconditions, but efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists so return values need not be described, and behavior gates are covered, but with 7 parameters at 0% schema coverage critical input semantics remain undocumented. Adequate but with a clear gap for a destructive mutation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not compensate: dataset_path, field_group_name, expected_dataset, confirmation, retired, and subtype are never explained. Only the value kinds are hinted at, leaving six of seven parameters semantically opaque.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (添加) plus resource (contingent values) and the value kinds it handles (ANY/NULL/CODED_VALUE/RANGE), which clearly separates it from list/remove/export/import siblings. Clear purpose, though it does not name an alternative sibling the way a 5 would.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies usage through prerequisites (double-gate for scheme change, exact target echo, fixed confirmation phrase) but never states when to pick this over siblings or when not to use it. Usage is inferable rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds that the connection is root-constrained and can be made the default geodatabase, but says nothing about permission requirements, behavior when the connection already exists, or validation of the database path.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no wasted wording; the core action and its constraints come first. It is efficient, though brevity contributes to the parameter-coverage gap.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and annotations carry the mutation/safety profile. However, for a mutation tool with 4 parameters at 0% schema coverage, the description is too thin to tell the agent how to supply aprx_path, database_path, and validate correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, yet it only obliquely references make_default via '可设为默认地理数据库' and never explains aprx_path, database_path, or validate. With four undocumented parameters, the description leaves a substantial gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('追加一个数据库连接' = append a database connection) and adds scope ('受输入根约束' = constrained by the input root) plus an optional effect (can be default geodatabase). It separates add from remove via the sibling name, but does not differentiate itself from the closely related arcgis_pro_create_db_connection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No statement of when to use this tool versus alternatives such as arcgis_pro_create_db_connection or arcgis_pro_add_folder_connection, and no prerequisites or exclusions are given. The agent must infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds no behavioral context beyond that — nothing about side effects on existing topology rules, whether ranks must be unique, or whether the change is persisted immediately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler, which is structurally clean. However, for a four-parameter mutation tool the brevity reflects under-specification rather than earned conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. But for a non-idempotent, non-read-only topology mutation, the description supplies no prerequisites, no post-conditions, and no parameter semantics — a significant gap given the 0% schema coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for four parameters. It only gestures at xy_rank/z_rank ('设置 XY/Z rank') and ignores topology_path and feature_class entirely, adding almost no meaning beyond the schema titles. The rank semantics (what higher/lower rank means for coincident geometry) are left unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb+resource ('把要素类加入拓扑' — add a feature class to a topology) and names the tunable ranks, so an agent knows exactly what operation this performs. It does not distinguish itself from close siblings such as arcgis_pro_add_rule_to_topology or arcgis_pro_remove_feature_class_from_topology, so it stays below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this versus creating a topology, adding rules, or removing a feature class. It also omits prerequisites such as whether the topology must already exist or whether an edit/save is required afterward. The only usage information is implied by the verb itself.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare write (readOnlyHint=false), non-destructive, non-idempotent, closed-world behavior. The description adds the important constraint that the folder must be under the input root and mentions the home-folder option, offering modest context beyond annotations but not elaborating on side effects or validation behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single compact sentence that front-loads the core action and constraint. No wasted text, though the language mismatch with the English tool fields is a minor structural inconsistency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter mutation tool with 0% schema coverage and no output schema, the description covers the root constraint and home option but omits alias/validate behavior and return information, leaving it only partially complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides only parameter names and defaults. The description references the root constraint and home-folder option but leaves alias, validate, and the exact semantics of folder_path/aprx_path undocumented. It partially compensates but leaves gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb (add) and resource (folder connection to the project), distinguishing it from the many sibling tools like remove_folder_connection. The description is in Chinese while the tool name/title are English, which slightly muddies clarity but the intent is discernible.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage ('constrained to the input root', 'can be set as home folder') but gives no explicit when-to-use advice or alternatives (e.g., vs add_database_connection or remove_folder_connection). Usage is inferable but not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations declare idempotentHint=false, but the description states '已有 GlobalID 时跳过' (skip when GlobalID already exists), which implies repeated calls with the same arguments would have no additional effect—i.e., idempotent behavior. This directly contradicts the annotation. Although the description also adds useful details like the 50-dataset limit and per-dataset verification, the rule mandates a score of 1 for annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The entire description is one compact sentence that front-loads the action, scope, and key conditions. Every element—max 50, controlled .sde, verify each, skip existing—earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter mutation tool with an output schema and safety annotations, the description covers the critical operational boundaries: dataset type, count limit, verification, and idempotent-like skip behavior. The only notable omission is the expected format of dataset paths, and the annotation contradiction slightly undermines confidence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for the single dataset_paths parameter. The description partially compensates by implying the input is a set of controlled .sde datasets and capping it at 50, but it does not explain path syntax or format. This adds some meaning beyond the bare schema, but leaves a clear gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb-resource pair: add GlobalID to controlled .sde datasets, with a cap of 50 and skip-if-existing behavior. This distinguishes it from sibling tools like arcgis_pro_list_sde_datasets or arcgis_pro_describe, which inspect rather than mutate. An agent can identify the action without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear contextual guidance: use for controlled .sde datasets, up to 50 at a time, and skip datasets that already have a GlobalID. No explicit when-not-to-use or alternative tool is named, but the operational boundaries are sufficient for routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the write/safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds context beyond them: the operation is a mutation requiring an enterprise write gate and targeting an enterprise .sde dataset, plus a verification step. That is meaningful disclosure, though it omits reversibility or failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tightly packed sentence with the primary action front-loaded and the write-gate precondition trailing. It is efficient and free of filler, though the compressed style slightly reduces readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and annotations cover safety. Still, with 5 parameters at 0% schema coverage and no alternative-routing or permission details beyond the write gate, the definition is only adequate for a mutation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only loosely alludes to the fields ('exact field list') and says nothing about index_name, unique (NON_UNIQUE default), or ascending (NON_ASCENDING default). The two enumerated-style optional parameters are left entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (add attribute index), the resource (fields of a controlled .sde dataset), and an extra action (verify/review), which lets an agent distinguish it from remove_index or rebuild_indexes. It stops short of naming a sibling explicitly, so it is clear but not maximally differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It discloses a precondition (requires the enterprise write gate) and scopes the target to controlled .sde datasets, which implies when the tool applies. However, it gives no explicit when-to-use-versus-alternative routing against siblings like rebuild_indexes or remove_index.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, covering the safety profile. The description only adds generic boilerplate ('returns verifiable structured results; write and path restrictions subject to service capabilities') without stating permissions, reversibility, or what a join mutates in the project.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loads the tool name, but the brevity reflects under-specification rather than efficiency. Both sentences are generic filler that could apply to any tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values needn't be explained, but for a 6-required-parameter mutation tool with 0% schema coverage and no usage guidance, the description is far too thin to let an agent call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 7 parameters (6 required), so the description carries the full burden of explaining parameters like layer_field, join_field, and join_type. It mentions none of them, leaving field-matching and join-type semantics entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says 'add add join', which essentially restates the tool name and title rather than explaining what a join operation does to a layer and table. It adds no differentiating detail from siblings like arcgis_pro_add_relate or arcgis_pro_remove_join.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus remove_join, add_relate, or gp_spatial_join. No prerequisites, context, or alternative-selection logic is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the safety profile is covered. The description adds only a vague statement that write and path restrictions depend on service capabilities, and 'returns verifiable structured results' is generic when an output schema already exists. It does not disclose concrete mutation effects, permissions, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loads the action, which is structurally appropriate. However, the second sentence contains generic boilerplate about structured results and service-dependent restrictions rather than earning its place with useful specifics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter mutation tool with 0% schema coverage, the description is missing critical information about parameters, prerequisites, and behavioral effects. Annotations and the output schema cover safety and return shape respectively, but they do not compensate for the absent parameter semantics and usage guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three required parameters (aprx_path, map_name, data_path) have 0% schema description coverage. The description names no parameter and provides no format, path syntax, or map-selection meaning. It therefore fails to compensate for the complete absence of parameter documentation in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says only 'ArcGIS Pro: Add layer', which essentially restates the tool name and title. It does not distinguish this from close siblings such as arcgis_pro_insert_layer, arcgis_pro_add_layer_to_group, or arcgis_pro_add_table_from_path. The resource is clear, but the purpose is not specified beyond the title.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The only contextual clause, 'write and path restrictions subject to service capabilities', is a generic caveat rather than usage guidance. An agent receives no help choosing between this and sibling layer-insertion tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the safety profile is covered structurally. The description adds one useful behavioral fact beyond that: empty group layers are valid targets. It does not disclose what happens to layer ordering, whether the source layer is duplicated or moved, or what happens on name collisions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single compact sentence with the core operation front-loaded and no filler. It is not padded, though the terseness is part of why other dimensions are thin.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a non-idempotent mutation tool with 6 undocumented parameters and a 0% schema coverage, the description omits critical context: the role of aprx_path, the semantics of an empty source_map_name, and how add_position affects the result. Having an output schema excuses return-value explanation, but the input-side gaps remain substantial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there are 6 parameters (4 required), so the schema gives no semantic help. The description covers only three of them conceptually (source layer, target map, group layer) and says nothing about aprx_path, source_map_name (default empty string — presumably meaning same map), or add_position (default AUTO_ARRANGE). This leaves the ambiguity of cross-map moves and placement policy unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb and resource: moving an existing project layer into a target map's group layer. It implicitly distinguishes itself from siblings like arcgis_pro_insert_layer, arcgis_pro_copy_layer, and arcgis_pro_create_group_layer by scope (project layer into an existing group), though it never names an alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites (must the group layer already exist? must the source layer be in the same project or loaded in a map?), and no mention of the closest siblings such as copy_layer or insert_layer. The agent must infer selection criteria entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false). The description adds real value by disclosing the dual input mode and the input-root constraint on .stylx paths, but says nothing about persistence (whether the .aprx must be saved), error behavior, or overwrite semantics for an already-present style.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler; the operation is stated first and the two input forms follow. It is terse to the point of omitting guidance, but nothing in the text is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a two-required-parameter mutation tool with 0% schema coverage, the description leaves `aprx_path` undefined and offers no guidance on valid inputs or side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and neither parameter has a description in the schema. The description partially compensates by explaining that `style` may be either a system style name or a root-relative .stylx path, but `aprx_path` receives no explanation at all, leaving the compensation incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (append/add) and resource (project style), and distinguishes the two accepted inputs: a built-in system style name or a .stylx file. It is easily separable from the sibling arcgis_pro_remove_project_style, though it never names siblings explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives (remove_project_style, list_style_items) or of what happens on duplicate style names. Usage must be inferred entirely from the name and description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare non-readonly, non-destructive, non-idempotent, and non-open-world. The description adds important behavioral constraints beyond that: accepted controlled formats (.atbx/.tbx), rejection of executable .pyt, and ability to make the toolbox default. It still does not describe permission requirements or the mutation's exact effect on the project.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that packs purpose, format restriction, and default option with no filler. The semicolon structure is compact and readable, though the sentence is dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has annotations and an output schema, so safety and return values are partly covered by structured fields. However, with 4 parameters at 0% schema description coverage, the description leaves validate and aprx_path undocumented, so it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must carry the entire parameter burden. It partially covers toolbox_path (.atbx/.tbx, no .pyt) and make_default (可设为默认工具箱), but says nothing about aprx_path or the validate parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (追加/add) and resource (受控 .atbx/.tbx 工具箱) to a project directory, and includes a key constraint (拒绝 .pyt). It does not explicitly differentiate from other add_* siblings such as add_project_style or add_folder_connection, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no alternatives, no prerequisites. '可设为默认工具箱' describes a parameter effect, not a usage condition, and '拒绝可执行 .pyt' is a format constraint rather than guidance on when to invoke this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false. The description adds only that rasters come from 'controlled paths' and that duplicate/pyramid/statistic/thumbnail options can be limited, which mostly echoes parameter categories rather than disclosing mutation impact, permissions, or side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler. It is appropriately compact, though its extreme brevity for a 14-parameter mutation tool leaves it structurally underdeveloped relative to the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values are covered. But with 14 parameters, 0% schema description coverage, and no usage guidance, the description is far too thin to support correct invocation of this complex mosaic dataset operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 14 parameters. The description vaguely mentions duplicate items, pyramids, statistics, and thumbnails, loosely mapping to a few parameters, but provides no types, formats, defaults, allowed values, or meaning for the remaining 10 parameters, failing to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('把...加入' = add) and resource ('mosaic dataset'), making the core action clear and distinguishing it from remove/create mosaic dataset siblings. However, it does not explicitly differentiate itself from other add-style tools or name any alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no alternatives are named. The description just states the operation without helping an agent decide between this and sibling tools like create_mosaic_dataset or remove_rasters_from_mosaic_dataset.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already disclose readOnly=false, destructive=false, idempotent=false, and openWorld=false. The description adds the important behavioral detail that the relate is temporary, but does not discuss persistence, session scope, permissions, or side effects beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two brief clauses with no filler and front-loads the core action. It is concise, though the terseness contributes to gaps in parameter and prerequisite information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation tool with 0% schema coverage, the description is far too thin. It does not explain any parameter meaning, required inputs such as aprx_path/map_name/item_kind, or how the relate_table_path and input_field should be chosen.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are 9 parameters with 0% schema description coverage, and the description names none of them. Titles like 'Item Kind' and 'Input Field' do not explain accepted values, formats, or relationships between parameters, leaving the agent unable to confidently supply required inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a precise verb-resource pair ('add temporary relate') and explicitly scopes it to a layer or table view. It also distinguishes the operation from the sibling tool arcgis_pro_create_relationship_class by stating that permanent relationships should use that tool instead.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says to use this tool for temporary relates and directs permanent relationships to CreateRelationshipClass, which is a clear when/when-not split. However, it does not cover other adjacent tools such as add_join/remove_join or state prerequisites like needing an open project.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so safety is covered. The description adds only that a destination feature class can be specified; it says nothing about required preconditions (existing topology, participating feature classes) or what constitutes a valid rule_type, leaving the mutation's behavior largely opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, compact sentence with no filler, front-loading the core action. It is efficient, though arguably under-specified rather than optimally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but the mutation logic, prerequisites, and the four undocumented parameters are not addressed. For a topology-editing tool with 0% schema coverage, this leaves the agent without enough to construct a correct call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the parameter burden. It gestures at rule_type ('precision rule') and destination_feature_class, but provides no meaning for topology_path, origin_feature_class, or valid rule type values, and does not explain the origin/destination pairing semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (add) and resource (rule to topology), and clarifies that a destination feature class may be specified, which distinguishes it from the sibling remove_rule_from_topology. However, it does not explicitly contrast itself with the other topology siblings such as add_feature_class_to_topology or create_topology.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus alternatives, nor any prerequisites. An agent gets no indication that a topology must already exist or that the feature classes must already be included before a rule can be added.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations establish the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description need not restate it. But it adds nothing beyond that: it omits the near-certain prerequisite that a subtype field must already be set (see set_subtype_field), gives no hint about failure modes such as duplicate codes, and does not note that this is a schema-altering write.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short, front-loaded sentence with no waste, which is good for scanning. However, the brevity comes at the cost of under-specification rather than disciplined editing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but for a schema-modifying tool the description should still cover prerequisites and usage context, which it does not. Given 0% parameter coverage and a dense sibling cluster around subtypes, this is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, and it merely restates the parameter titles ('code', 'name', 'dataset') without adding meaning. No format, uniqueness, or type expectations are conveyed beyond what the bare titles already imply.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('add') and resource ('subtype code and name') applied to a dataset, so the core action is unambiguous. It does not, however, distinguish itself from nearby siblings like arcgis_pro_set_subtype_field, arcgis_pro_remove_subtype, or arcgis_pro_set_default_subtype, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus set_subtype_field, remove_subtype, or set_default_subtype, and no stated prerequisites. The agent is left to infer all routing decisions from the sibling names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is partly covered. The description adds only the vague note that write and path limits follow service capabilities, without saying what gets modified, what happens on conflict, or what permissions are needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded, but its brevity stems from generic boilerplate ('returns verifiable structured results') rather than tightly specified content. It is sized acceptably without being informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, but the description still lacks anything about the three required parameters, the target project/map context, or when the operation can fail. For a write tool with no annotation-based detail on effects, this is under-specified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters (aprx_path, map_name, table_path) have 0% schema description coverage and the description names none of them. The loose mention of 'path restrictions' hints at path handling but adds no format or meaning beyond the schema, leaving the required parameters effectively undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a verb and resource ('ArcGIS Pro: Add table'), which is minimally clear but essentially restates the tool name/title. It does not distinguish this from siblings like arcgis_pro_add_table_to_group, arcgis_pro_add_layer_from_path, or arcgis_pro_gp_create_table, so an agent cannot easily route between them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. The clause about write/path restrictions depending on service capability is a caveat, not a usage instruction, leaving the agent to infer when this tool applies.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation is mutating but non-destructive and non-idempotent (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the safety profile is covered. The description adds only that the table must be an existing standalone table already in the map, a useful prerequisite, but omits failure modes, permission needs, and what the mutation changes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler. It is efficient, though arguably too terse given the schema carries no parameter documentation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, but for a 4-parameter mutating tool with 0% schema coverage the description is far too thin. It should at least clarify the roles of aprx_path and map_name and any prerequisites for the operation to succeed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all 4 required parameters, so the description must compensate. It loosely maps to table_name and group_layer_name ('existing standalone table', 'target group layer') but says nothing about aprx_path or map_name, leaving half the parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (add) and resource (an existing standalone table) plus the target (a group layer), which is clear enough to distinguish from the sibling add_layer_to_group. However, it does not explicitly name or contrast with that sibling, so an agent must infer the layer/table distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance, no prerequisites, and no alternatives. It does not tell the agent how this differs from add_table_from_path or add_layer_to_group, leaving selection to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds only the list of updatable properties and does not disclose side effects, required permissions, or consequences of renaming or changing domain ownership.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler. Every listed item corresponds to an actionable alteration, so it is appropriately sized for the description's scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 7 parameters, no schema descriptions, and no output-schema concern for the description. The definition omits required-parameter meaning, usage context, and behavioral details, making it too thin for a domain-alteration operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It names the mutable attributes (name, description, split/merge policy, owner), which maps to several optional parameters, but it does not explain workspace_path or domain_name, and gives no syntax or default information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (更新) and resource (属性域) and lists the mutable aspects: name, description, split/merge policy, owner. It is clear enough to distinguish from domain creation/deletion by implication, but it does not explicitly name alternatives or boundaries against sibling domain tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as create_domain or delete_domain. The agent is left to infer that this tool alters an existing domain.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

'Register a physical file version and GIS role' describes a write/registration action, yet the annotations declare readOnlyHint=true and idempotentHint=true. This is a direct tension between the description's mutation framing and the read-only annotations, and the description adds nothing about permissions, persistence, or side effects to resolve it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded into a single line, so it wastes few words, but the terseness comes at the cost of cryptic, unexplained terminology rather than genuine economy. Appropriate length, weak information density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, but with 0% parameter coverage, a mutation/read-only contradiction, and no usage context, the definition is not complete enough for an agent to call this tool confidently. It should clarify identity_basis and the relationship between registration and the read-only annotation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across all four parameters, so the description carries the full burden. It gestures at 'role' and 'file version' but never explains dataset_path, identity_basis, or vector_layer, leaving three required parameters effectively undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a verb ('Register') and resources ('physical file version and GIS role'), which is more than a tautology, but the phrasing is dense jargon and it conflicts with the name/title ('Analysis Asset Info'), which suggests a query rather than a registration. It also does not distinguish this tool from analysis-adjacent siblings like arcgis_pro_analysis_result_status or arcgis_pro_validate_analysis_environment.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'File mode; no GUI selection' gives a sliver of operating context, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many sibling analysis tools. The agent is left to infer the scenario in which registration is required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true and non-destructive, so the safety profile is covered. The description adds a warning about not inferring success from files, but does not disclose what the validation checks, what 'evidence' means, or what the response contains. With an output schema present the return shape is covered, but behavioral context beyond annotations is thin.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single compact sentence with no filler. It is front-loaded but very terse for a tool whose purpose is not self-evident from the name alone.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a status/validation tool with an output schema and read-only annotations, the description should at least clarify what status is returned and how it relates to sibling verification tools. Instead it offers only a terse warning, leaving the agent to guess the return semantics and the relationship to arcgis_pro_verify_output_dataset.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there is one required parameter (run_id). The description mentions 'checked-run' but does not explain what a run_id identifies, where it comes from, or its format. Baseline is 3 for a one-parameter tool; the description adds little.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description implies the tool validates/revalidates analysis result status, but it never states a specific verb+resource like 'get the status of a checked analysis run'. It names 'checked-run evidence' and 'file versions' which hints at scope, but the purpose is vague enough that an agent can't confidently say what the tool returns.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The closing clause 'never infer success from file existence' implies the tool should be used to verify success rather than inferring it, but it doesn't explicitly say when to use this vs alternatives like arcgis_pro_verify_output_dataset or arcgis_pro_gp_job_status. Usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds that the operation touches three specific table categories and requires an enterprise write connection, but says nothing about cost, locking, or runtime impact on a large enterprise geodatabase.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short sentence with the scope front-loaded and no filler, but it is terse to the point of under-specification for a 6-parameter mutation tool; the brevity costs more than it saves here.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, but for a write-operation tool with 6 undocumented parameters and only annotations for safety, the description leaves too much unexplained. An agent cannot tell what include_system or the analyze_* flags actually do.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 6 parameters, so the description carries the full burden and largely fails it: datasets, workspace_path, and include_system are never explained. The mention of 'base/delta/archive tables' loosely maps to analyze_base/analyze_delta/analyze_archive but does not clarify their semantics or defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource: updating statistics on enterprise geodatabase base, delta, and archive tables. This is far more specific than the tool name alone and distinguishes it from read/maintenance siblings like dataset_maintenance_info or rebuild_indexes, though it does not explicitly compare itself to them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states a prerequisite ('requires enterprise write permission/write connection'), which is useful context, but gives no guidance on when to choose this tool over related maintenance siblings such as workspace_list_datasets, dataset_maintenance_info, or rebuild_indexes. No exclusions or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-read-only, non-destructive, idempotent operation, so the safety profile is covered. The description adds the behavioral detail that duplicate symbol names are disambiguated by index, but it does not describe permissions, side effects, or what happens when no symbol matches the wildcard. With annotations carrying the main behavioral burden, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is front-loaded with the core action and contains no filler. It is compact and direct, though the extreme brevity contributes to gaps in other dimensions rather than representing excessive length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with five parameters, zero schema descriptions, and no output schema explanation needed, the one-sentence description is too thin. It omits usage context, most parameter semantics, and behavioral details about the application of the symbol. The presence of an output schema covers return values, but the input-side gaps remain large.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for five undocumented parameters. It only explains the index parameter, stating it disambiguates duplicate names. It does not explain wildcard, aprx_path, map_name, or layer_name, leaving most parameter meaning to the agent's inference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action: applying a matching symbol from the project symbol gallery to a SimpleRenderer. It also names the mechanism for resolving duplicate symbol names via index. It does not explicitly differentiate from siblings such as arcgis_pro_set_simple_renderer or arcgis_pro_apply_symbology_from_layer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives. It does not mention prerequisites, when the gallery should be used instead of applying symbology from a layer, or any conditions or exclusions. Usage is only implied by the purpose statement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint=false, idempotentHint=true, destructiveHint=false, giving the safety profile. The description adds only a vague note about write and path limits being service-dependent, which is generic boilerplate and does not say what state is modified, what permissions are required, or how the symbology layer is sourced. It doesn't contradict annotations, but adds little beyond them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short but under-specified rather than concise. The two clauses are boilerplate and do not front-load any actionable information about what the tool does.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-required-parameter mutation tool with 0% schema description coverage, the description is drastically incomplete. It omits required context about the operation, its inputs, and its effects, while an output schema exists but the description doesn't leverage or explain the tool's behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% — all four parameters (aprx_path, map_name, layer_name, symbology_layer_path) are completely undocumented in both schema and description. The description doesn't compensate at all, leaving the agent with no guidance on parameter meaning, format, or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says "ArcGIS Pro: apply layer" which restates the tool name/title without adding a specific action or resource. It doesn't mention symbology, aprx, map, or any of the four required parameters, so an agent cannot distinguish it from siblings like arcgis_pro_copy_layer or arcgis_pro_set_simple_renderer. This is essentially tautological.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use, when-not-to-use, prerequisites, or alternatives are stated. The tool has many rendering-related siblings (set_unique_value_renderer, set_simple_renderer, apply_gallery_symbol) and the description gives no guidance on choosing between them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already disclose this is a non-read-only, idempotent, non-destructive, non-open-world mutation, and the description does not contradict them. However, it adds nothing beyond the annotations: it does not say what gets altered (the dataset schema), whether the change overwrites an existing domain assignment, or what permissions/preconditions apply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no wasted words, which is good. But for a 4-parameter schema-mutating tool it is arguably under-specified rather than genuinely concise, so it lands at the minimum-viable level.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but this is a mutation tool with zero schema description coverage and only annotation-level behavioral disclosure. It omits preconditions, the effect on existing assignments, and parameter meaning, leaving real gaps for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden but only hints at the optional subtype_code constraint. dataset_path, field_name, and domain_name are self-evident from their names, but subtype_code's meaning (a subtype code value used to scope the assignment) is barely conveyed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('assign domain to field') and notes the subtype-code scoping, so an agent can tell this is a schema-editing operation distinct from read-only domain listing. It does not, however, differentiate itself from the sibling arcgis_pro_remove_domain_from_field or the other domain tools, so a 4 rather than 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisite (e.g. that the domain must already exist via arcgis_pro_create_domain), and no mention of alternatives such as arcgis_pro_remove_domain_from_field. The only conditional hint is that subtype_code may optionally narrow the assignment.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered by structured metadata. The description adds the specific information content (attachment enablement status and relationship class name), but does not disclose additional behavioral traits such as permissions, path constraints, or execution context. With annotations carrying the safety burden, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler or redundancy. It immediately states the action and the information retrieved, and every part of the sentence contributes meaning. Nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the description does not need to explain return values, and annotations fully cover the read-only, idempotent, non-destructive profile. The description clearly states what information is read. The main remaining gap is the lack of any detail about the dataset_path parameter format, which slightly limits completeness for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one required parameter, dataset_path, and schema description coverage is 0%, so the description must compensate. It implies a dataset is the input via '数据集' but does not explain what form dataset_path takes, whether it is a feature class, table, or layer path, or any constraints. This is a significant gap for the only parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific read operation on a named resource: whether a dataset has attachments enabled and the related relationship class name. This clearly distinguishes it from sibling tools like enable_attachments, disable_attachments, add_attachments, and remove_attachments. An agent can tell what the tool does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance, no prerequisites, and does not name alternatives or exclusions. It only states what is read, leaving the agent to infer that this is the tool for checking attachment configuration. No explicit routing to or away from sibling tools is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false). The description adds two pieces of context beyond that: the binding is 'explicit' and a URI is read back for verification, which hints at a confirmable/idempotent mutation. It does not say whether an existing binding is overwritten, what happens on failure, or whether the project must be saved.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single compact sentence with the action front-loaded and no filler. It is efficient, though the brevity is partly the cause of the semantic gaps noted elsewhere.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool that binds a layout element to a map, the description omits preconditions, overwrite behavior, and any note on the returned URI even though an output schema exists. The output schema excuses return-value prose, but the missing operational context leaves it inadequate for confident invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and all four required parameters (aprx_path, layout_name, mapframe_name, map_name) are documented only by their titles. The description does not explain any of them, such as the expected path format for aprx_path or how names are resolved, so it fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('绑定' / bind) and resource ('布局地图框' / layout map frame) plus the target ('地图' / map), which cleanly separates it from siblings such as list_layout_map_frames, mapframe_extent, or set_mapframe_extent. It is clear but never names or contrasts an alternative sibling, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when this tool should be used instead of alternatives, no prerequisites (e.g. project/layout must exist, view state), and no exclusions. For a among ~250 sibling tools in the layout/mapframe family, a 'when to use' cue is especially valuable and is entirely absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare that this is a non-read-only, idempotent, non-destructive operation. The description adds useful context by saying it builds or updates a display pyramid and can use constrained class-code weights, but it does not disclose side effects, permissions, or where the pyramid is stored.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler, and the core purpose comes first. It is appropriately terse, though adding no structural breakdown for a four-parameter mutation tool keeps it from being maximally helpful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and annotations cover safety. However, with zero schema descriptions, two required parameters, and no usage guidance, the description is incomplete for a LAS pyramid build/update operation; it omits what 'expected_las_dataset' means and how point selection affects the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters, so the description must compensate. It mentions '.lasd' and 'class-code weights' for two parameters, but leaves 'expected_las_dataset' and 'point_selection_method' (default Z_MIN) entirely unexplained, which is a significant gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific operation ('构建或更新显示金字塔') on a specific resource ('.lasd'), which lets an agent identify it as a LAS dataset pyramid tool rather than a raster pyramid or LAS statistics tool. It does not explicitly name or contrast sibling alternatives, but the verb+resource combination is clear enough.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives such as arcgis_pro_raster_build_pyramids, arcgis_pro_las_dataset_info, or arcgis_pro_calculate_las_statistics. The phrase '精确确认的 .lasd' hints at a pre-condition but is not explained.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds one genuine behavioral trait beyond that — it reads back and verifies the target after updating — but says nothing about what footprint geometry is modified, permissions, or side effects on the mosaic dataset.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short sentence with the action front-loaded, so there is no waste. But brevity here stems from under-specification rather than disciplined conciseness, and the 'fixed parameters' clause is noise for a 17-param tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 17-parameter raster/mosaic maintenance operation, the description is grossly incomplete: no guidance on the footprint-building parameters, no usage context, no alternatives. The presence of an output schema excuses it from explaining return values, but that does not offset the missing operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 17 parameters, and the description contributes no parameter meaning at all — not even the required in_mosaic_dataset or the many tolerance/size/simplification knobs. With the schema silent and the description silent, an agent must guess every argument.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a verb (update) and resource (mosaic dataset footprints), which is enough to distinguish it broadly from siblings like build_mosaic_overviews. However, the qualifier '以固定参数' (with fixed parameters) is confusing and even misleading for a tool exposing 17 configurable parameters, and no sibling (e.g. arcgis_pro_build_mosaic_overviews, arcgis_pro_add_rasters_to_mosaic_dataset) is named or contrasted.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to run this tool versus alternatives, no prerequisites (e.g. dataset must exist and contain rasters), and no conditions or exclusions. The phrase '并读回核验目标' hints at a verify-after-write workflow but is not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds that only missing or stale overviews are touched, which is useful behavioral context, but it omits what 'controlled targets' means and any prerequisite or cost information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler, and the core operation leads. It is efficient, though the brevity tips toward under-specification given the 7-parameter surface.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, but for a 7-parameter mutation with 0% schema coverage and no usage guidance, the description leaves major gaps. An agent cannot determine parameter intent or safe invocation from this text alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 7 parameters, so the description must compensate and largely fails. The mention of 'missing or stale' loosely maps to generate_missing_images and regenerate_stale_images, but define_missing_tiles, generate_overviews, where_clause, and environment receive no explanation anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb pair (define and generate) and resource (mosaic dataset overviews) plus the scope constraint (missing or stale). An agent can grasp the operation, but it never distinguishes itself from siblings like arcgis_pro_build_mosaic_footprints or arcgis_pro_raster_build_pyramids.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use, when-not-to-use, or alternative guidance. 'Limited to controlled targets' hints at scoping but never explains what a controlled target is or when this should be chosen over other mosaic maintenance tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so safety is covered. The description adds one genuinely useful behavioral fact beyond the annotations: it does not create a dataset ('不创建数据集'), telling the agent this is a value-returning computation rather than a data-producing tool. It does not disclose units, distance-method effects, or any limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler; the key computation leads and the non-output caveat follows. Efficient, though arguably under-specified rather than optimally concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and the non-dataset note is helpful. But with 0% parameter coverage and no usage context, the definition is only minimally sufficient for a geoprocessing analysis tool an agent must invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and there are 4 parameters. The description clarifies number_of_neighbors (the required neighbor count that defines the threshold) and implies in_features ('每个要素'), but says nothing about distance_method (default EUCLIDEAN_DISTANCE) or environment, leaving half the params undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('计算...距离阈值' / calculate the distance threshold) and scopes it precisely: the threshold where each feature has at least the specified number of neighbors. It does not name or contrast any sibling (e.g. generate_spatial_weights_matrix, average_nearest_neighbor), so an agent cannot disambiguate among the many analysis tools from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. The description only says what is computed, not when an agent should pick this over the neighboring spatial-statistics tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description correctly discloses a destructive-gate workflow with target echo and fixed confirmation phrase for forced recompute — going beyond annotations. However, it conflicts in spirit with destructiveHint=false and idempotentHint=true annotations, since '强制重算' (forced recompute) and an overwrite confirmation imply mutation of existing stats; the annotations reduce the safety disclosure burden but the description's gating language doesn't fully explain the mismatch.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single compact sentence with no filler, but it front-loads the destructive-gate mechanics while omitting more basic operational context, so information density is uneven.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An 8-parameter mutation-adjacent tool with 0% schema coverage and no output schema mentioned in the description; the description covers only the overwrite-gate path and neglects the default SKIP_EXISTING_STATS flow and report output semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description names only las_dataset, expected_las_dataset (target echo), and the confirmation phrase concept. It does not explain summary_level, calculation_type, delimiter, decimal_separator, or out_report — six undocumented parameters left to the agent to infer.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear specific verb (calculate) plus resource (LAS statistics) and mentions report export, distinguishing it from sibling arcgis_pro_las_dataset_info and arcgis_pro_build_las_pyramid. The destructive-gate phrasing is unusual but purpose remains identifiable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus arcgis_pro_las_dataset_info or arcgis_pro_build_las_pyramid, and no explanation of the calculation_type enum values (e.g., SKIP_EXISTING_STATS) that clearly gate behavior. The '强制重算' (forced recompute) phrasing hints at a mode but doesn't state when to choose it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already state readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds an authorization requirement not present in the annotations ('requires enterprise write access'), which is genuinely useful behavioral context about prerequisites. It stops short of describing side effects on unsaved edits or lock behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler; the scope ('uniquely matched layer or standalone table') and the prerequisite are both conveyed compactly. It is efficient, though very terse for an 8-parameter mutation tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. However, for a mutation tool with 8 undocumented parameters at 0% coverage, the description omits key mechanics: how the layer/table is matched, the role of member_type, history_date, version_name, and include_participating. It is not complete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 8 parameters, so the description must compensate but only partially does: it implies the values for version_type (traditional/historical/branch) but says nothing about aprx_path, map_name, member_name, member_type, history_date, version_name, or include_participating, leaving most parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (切换到/switch to) and resource ( uniquely matched layer or standalone table in the project), plus the version categories it targets (traditional, historical, branch). This clearly separates it from siblings like list_versions, create_version, reconcile_versions, and post_version, though it does not name a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a real precondition ('requires enterprise write access/gateway') and enumerates the version types, which helps the agent understand context, but there is no explicit when-to-use vs. when-not guidance nor any named alternative such as reconcile_versions or post_version.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds the useful behavioral detail that it reads fields, axes, and display properties, but it does not add auth requirements, rate limits, or failure behavior beyond what the output schema and annotations cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence that communicates the core action and lookup key without filler. It is appropriately sized for a read-only chart-info tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not detail return values, and annotations cover the safety profile. However, because all five input parameters have 0% schema description coverage, the description is incomplete enough that an agent may not understand how the chart is scoped by project, map, and member context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for five parameters, so the description carries the burden. It only clarifies that title is the unique lookup key and that the chart is a typed ArcPy chart, leaving aprx_path, map_name, member_name, and member_type unexplained in the description or schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb-resource pair: read a typed ArcPy chart's fields, axes, and display properties by unique title. It is clearer than a generic chart-info tool, though it does not explicitly contrast itself with sibling tools such as arcgis_pro_list_charts or arcgis_pro_export_chart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says the chart is identified by unique title, which implies when it might be used, but it gives no explicit when-to-use or when-not-to-use guidance. It also does not point to alternatives for listing, exporting, or modifying charts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds one behavioral boundary: chart deletion without a supported ArcPy API is explicitly rejected. It does not describe return format, error shape, or how other mutation capabilities are reported.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one compact sentence with two useful clauses: the primary read action and the current deletion limitation. It is front-loaded and waste-free, though the second clause could be slightly more explicit about what is being rejected.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, an output schema, and annotations covering safety, the description is largely complete for a capabilities-query tool. It states the purpose and one important mutation boundary, though it does not preview what categories of chart mutations are considered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameter meaning, and the empty input schema plus 100% coverage correctly indicate that the tool takes no arguments.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('read chart mutation boundaries') and adds the current limitation that unsupported chart deletion is rejected. This is clearer than a bare tautology, but it does not distinguish the tool from siblings like arcgis_pro_list_charts, arcgis_pro_chart_info, or arcgis_pro_upsert_chart. The resource term 'mutation boundaries' remains somewhat abstract.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to call this tool versus the sibling chart tools. It mentions one supported/rejected boundary condition, but that is not framed as usage advice or as an alternative-selection rule. An agent must infer the tool's role from its name and title.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare non-read-only, non-destructive, idempotent. Description adds that it confirms the actual selection set is empty, a behavioral detail beyond annotations. It doesn't detail exception handling, but for a simple idempotent operation this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single front-loaded sentence with no wasted words; purpose, scope, and confirmation are all included.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Description is complete enough for a simple selection-clearing tool: purpose, scope, and confirmation are present, and annotations cover safety/idempotency. Return values are handled by the output schema, though usage guidance is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, description compensates partially by distinguishing between clearing a specified layer vs all feature layers, which maps to layer_name and scope. It doesn't name parameters or clarify scope values/defaults, but core semantics are conveyed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (清除/clear) and resource (选择/selection) with scope: specified layer or all feature layers. It doesn't explicitly name alternatives like delete_layer_selection, but the scope and confirmation behavior make it distinguishable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance. It doesn't mention alternatives or prerequisites, leaving the agent to infer context from the purpose alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds the non-obvious gating requirement that a destructive switch plus confirm=true must be supplied — information absent from the schema (0% coverage). It does not explain the effect on existing subtype-coded features, so it stops short of full disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence that front-loads the action and follows with the precondition; no filler. Slightly terse for a destructive mutation, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need no explanation, and annotations cover the safety profile. However, for a destructive schema-editing operation the description omits what happens to features whose subtype codes were assigned and whether the action is reversible, leaving the agent with an incomplete picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 2 parameters. The description explains confirm semantics (must be true), which is real added value, but dataset_path is left completely unexplained in both schema and text. Partial compensation only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('清除' = clear) plus resource ('数据集的子类型字段'), so the agent knows exactly what is affected. It does not distinguish itself from siblings such as arcgis_pro_set_subtype_field or arcgis_pro_remove_subtype, which is the main gap.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States a precondition ('需要破坏性开关及 confirm=true'), which tells the agent how to invoke it safely, but gives no when-to-use guidance, no exclusions, and never points to the alternative subtype tools (set/remove/add).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

注解已声明 readOnlyHint=false、destructiveHint=false、idempotentHint=true，说明这是非破坏性且幂等的操作；描述进一步补充了“不改数据”“含底图”以及“layer_name 为空则取消裁剪”等行为细节。这些是注解未覆盖的有价值上下文，但未说明裁剪状态是否持久化等其他行为。

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

仅两句话，信息前置且无冗余，第一句说明核心动作和约束，第二句说明取消条件。表述紧凑，直接服务于工具调用。

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

已有输出 schema，因此描述无需解释返回值；注解也提供了安全性和幂等性信息。但参数 schema 覆盖率为 0%，而描述只解释了 layer_name，未说明 selection 和 aprx_path 的用法，对完整调用而言仍有关键缺口。

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

参数 schema 描述覆盖率为 0%，描述必须承担解释参数的责任。描述只说明了 layer_name 为空时的语义，未解释必需的 aprx_path，也未说明 selection 参数的作用及默认值 ALL，三个参数中仅覆盖了一个。

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

明确说明了具体动作、对象和范围：按多边形图层轮廓裁剪当前地图的图层显示（含底图），且不改数据。与 arcgis_pro_gp_clip 等数据裁剪工具的差异也通过“不改数据”和“图层显示”被清晰区分。

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

给出了 layer_name 为空时取消裁剪的条件，属于使用上下文，但未明确说明何时该用本工具而非 arcgis_pro_gp_clip 等替代工具。使用场景主要是隐含的，而非显式引导。

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is clear. The description adds the window-scope constraint but does not disclose what actually happens to the views (unsaved state, whether it closes all or selected views), leaving some behavioral ambiguity for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that conveys the action, the target resources, and the scope constraint with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, so return values need not be explained. But for a 2-param mutation tool with 0% schema coverage and no annotations on view types, the description should explain view_type options and what 'close' entails (e.g., unsaved changes), which it omits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters. The description only restates the aprx_path=CURRENT requirement, adding no meaning to view_type (default MAPS_AND_LAYOUTS) or its possible values. It fails to compensate for the complete lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (关闭/close) and resource (地图、布局、报表或表视图) with the exact scope (当前窗口). Distinguishes it from siblings like arcgis_pro_open_report_view and arcgis_pro_list_temporary_views by naming the view types it closes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clarifies the constraint that aprx_path must be CURRENT, which tells the agent when this tool is applicable. However, it does not name alternatives (e.g., release_temporary_view, detach_window) for closing views in other contexts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already disclose non-read-only, idempotent, non-destructive behavior, so the bar is lower; the description still adds real value by explaining the token-validation guard and the staleness/tamper rejection semantics. A useful behavioral disclosure not present in annotations, though it omits what happens to already-repaired connections.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence that front-loads the action and then the guard condition. No filler; every clause contributes, though the grammar is packed and could be split for readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and the safety annotations cover part of the behavior. However, for a mutation tool with 0% schema coverage, the description leaves the required preflight workflow and the aprx_path parameter ambiguous for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the load. It clarifies that repair_token is a preflight token and that repairs constitutes a 'repair plan', which maps two of three params, but aprx_path and the internal shape of the repairs array remain unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: applying bulk data source repairs to a project. The precondition clause ('only when the repair plan and target connections are unchanged') further narrows scope, and the pairing with arcgis_pro_connection_repair_preflight is inferable. It does not explicitly name the preflight sibling, so it falls just short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a preflight token must exist and be fresh, which hints that a preflight step must precede this call, but it never states 'run arcgis_pro_connection_repair_preflight first' or contrasts with alternatives like arcgis_pro_repair_layer_source. Usage is implied rather than prescribed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds genuinely new behavioral facts: a hard cap of 100 repair targets, the token being signed, short-lived, and bound to the current connection digest (implying invalidation if the connection changes). Token TTL and failure modes are still unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with no filler, and the core action is front-loaded. It is efficient, though the terse one-liner leaves no room for the workflow context the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is not required, and annotations carry the safety profile. However, for a preflight step in a two-phase repair workflow, the description omits the relationship to arcgis_pro_connection_repair_apply, the token lifetime, and the structure of repair entries — gaps that matter for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both required parameters. The description partially compensates for 'repairs' by implying an array of up to 100 layer/table targets, but says nothing about the shape of each repair entry and nothing at all about 'aprx_path', which is undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and artifact — generating a short-lived signed preflight token for repairing up to 100 layer/table data sources. It is clearly distinguishable from generic list/describe tools, but it never names or references the sibling arcgis_pro_connection_repair_apply, so the two-phase preflight/apply pattern is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, and no alternative is named. The agent must infer from the name alone that this is a precursor step to arcgis_pro_connection_repair_apply and that the emitted token is the input to that call.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the safety profile is covered. The description adds useful context that the layer is placed at the top of the target map and that a new layer identifier is returned, but it omits whether the source layer is left untouched, whether overwrite/duplicate handling exists, and any permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler, and the primary action plus return value come first. It is efficient, though the extreme brevity is arguably part of why the parameter and usage gaps exist.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, and annotations cover the mutation/safety profile. However, for a 5-parameter cross-map mutation with 0% schema coverage, the description supplies no guidance on aprx_path, placement behavior, or failure conditions, leaving an agent under-informed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, so the description carries the full burden and largely fails: aprx_path and add_position are never mentioned, and source_map_name vs target_map_name are only implied. Worse, the description asserts the copy lands on the top layer, which sits awkwardly with the add_position parameter (default AUTO_ARRANGE) that evidently controls placement.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (复制/copy), a resource (工程中现有图层) and the destination (另一地图的顶层), plus a return value (新图层标识). It is clear on its own, but it never distinguishes itself from close siblings such as arcgis_pro_move_layer or arcgis_pro_insert_layer, so an agent cannot route between them from the text alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus move_layer, insert_layer, or add_layer_from_path, and no prerequisites (e.g. map must exist, layer must not already be in the target). Usage can only be inferred from the word 'copy'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare write behavior (readOnly=false, idempotent=false, destructive=false), so the safety profile is covered. The description adds meaningful behavior beyond that: bookmarks are created from the active map view or a specified layout mapframe, and duplicate names are rejected.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero wasted words. It states the action, source options, and duplicate-name rejection compactly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema covers return values and annotations cover write behavior, so the description need not explain results. However, with six parameters and 0% schema description coverage, the description leaves aprx_path and several parameter meanings undocumented, making it only minimally complete for reliable invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for six parameters. The description clarifies the source selection, which partly maps to source_type, layout_name, and mapframe_name, but it does not explain aprx_path, name, or description semantics. It compensates only partially for the missing schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.