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

No annotations are provided, so the description carries the full burden. It discloses rich return contents (columns with nullability/defaults/comments, constraints, indexes, view SQL, partition lists) and schema resolution behavior (auto-search non-system schemas, error on ambiguity). It does not explicitly state read-only status or permission needs, but for an introspection tool this is substantial 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?

Front-loaded with purpose, followed by usage context and then parameter notes, with no filler. The final clause repeats table/schema details already documented in the input schema, which slightly reduces 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?

With no output schema and no annotations, the description supplies necessary return-value details and parameter resolution behavior, enough for correct invocation. It does not cover instance selection (left to the schema) or explicit read-only assurance, but those gaps are minor for a describe 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 100%, so the baseline is 3. The description mostly restates details already present in the schema (table required, schema ambiguity handling) and omits the instance parameter entirely, adding little meaning beyond the structured fields.

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 (查看表/视图的完整结构) and enumerates the exact artifacts returned: columns, keys, constraints, indexes, view SQL, and partitions. It is unmistakably distinct from siblings like list_tables, list_schemas, and execute_select.

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?

Provides a clear use case (编写或校对查询前了解表结构、关联键与索引设计) and cross-references list_tables as a source for the required table parameter. It also warns about schema ambiguity. It lacks an explicit when-not statement or a named alternative such as execute_select for retrieving data.

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?

With no annotations, the description carries the full behavioral burden and does so well: it enumerates what is rejected (DML/DDL, SELECT INTO, FOR UPDATE/SHARE row locks, multi-statement, dangerous functions) and states that execution happens inside a server-enforced read-only transaction. It also discloses that max_rows defaults to instance config and is bounded by a server hard cap, which is exactly the kind of constraint an agent needs to avoid failed or oversized calls.

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 text is front-loaded with the core purpose, then constraints, then usage, then the max_rows note — a logical progression with no filler. It is dense but every clause about rejection rules earns its place; the closing max_rows sentence is mildly redundant with the schema description.

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-free query tool with no annotations and no output schema, the description supplies the safety profile (read-only transaction, rejected statement types), the workflow position relative to siblings, and the row-limit behavior. An agent has everything needed to construct a valid call and anticipate rejection conditions.

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 100%, so the schema already documents sql, instance, and max_rows, giving a baseline of 3. The description largely restates those constraints (single SELECT/WITH, default row limit, server cap) without adding syntax, format, or error-handling detail beyond the schema; the instance parameter is not elaborated on 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 (execute a read-only SELECT query) and immediately frames scope: '本服务器唯一允许的 SQL 入口' (the only allowed SQL entry point on this server). It also distinguishes itself from siblings by describing the workflow with list_tables/describe_table as the locating step, so an agent can tell it apart from the metadata tools without opening any 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?

Usage is explicit: use it after locating a target via list_tables/describe_table for data exploration and statistics (counts, aggregation, sampling, top-N ordering). It also gives an operational alternative rule — prefer LIMIT or aggregation for large result sets to reduce transfer. Both when-to-use and the sibling workflow are stated, leaving little 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?

With no annotations, the description carries the full burden and does well: it discloses the default system-schema exclusion, the optional inclusion of pg_catalog/information_schema, and the returned payload (object counts and comments). It does not explicitly state read-only semantics or any permission constraints, which keeps it short of a 5.

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?

Well front-loaded: purpose and default behavior first, then usage scenario, then the include_system caveat. Slightly dense for a two-parameter list tool, but each clause (defaults, usage order, system-schema caveat) carries distinct 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?

No output schema or annotations exist, and the description compensates by naming the returned fields (object counts, comments) and the default filtering behavior. Near-complete for such a simple tool; only explicit read-only confirmation 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?

Schema description coverage is 100%, so both parameters are already documented in the schema; the baseline is 3. The description reinforces include_system's default and motivation but adds little syntax or format detail beyond the schema itself.

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 ('list schemas in GaussDB'), plus what each entry contains (object counts and comments) and the default exclusion of system schemas. It is immediately distinguishable from siblings like list_tables, which it explicitly routes to.

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?

Gives explicit when-to-use ('the first step in exploring the database'), the follow-up action ('then use list_tables to view tables'), and a narrow condition for the include_system alternative ('generally only when troubleshooting system objects'). No inference 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?

With no annotations, the description carries the full burden and does well: it discloses the exact result fields, the default scan scope (all non-system schemas when schema is omitted), and a performance caveat for large databases. It stops short of stating permission/auth requirements or ordering/pagination, but covers what an agent needs to invoke it safely.

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?

Front-loaded with the resource and return fields, then usage and the filtering tip. Every sentence carries information, though the final sentence partially restates the schema-omission behavior already stated earlier.

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?

No output schema exists, so the description must explain returns, which it does by listing the returned columns. Combined with usage routing and the filtering/performance caveat, nothing an agent needs to call this correctly is 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 coverage is already 100%, so the baseline is 3, but the description adds real value beyond the schema by explaining where the schema value comes from (list_schemas output) and why to supply it (narrow scan range). Remaining parameters are only reinforced, not extended, so it lands at 4.

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 (list tables/views in GaussDB) and enumerates exactly what the result contains (name, type, estimated row count, comment). It clearly distinguishes itself from siblings by naming describe_table, execute_select and list_schemas by their distinct roles.

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?

Gives explicit when-to-use guidance: locate a table here, then use describe_table for structure or execute_select for sampling. It also names the alternative source of the schema value (list_schemas) and the large-database condition that favors passing schema.

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?

With no annotations, the description must carry the behavioral burden, and it does disclose the observable outcome (version, current DB, user, read-only status, latency) plus the read-only transaction angle, which signals a non-mutating probe. It stops short of explicitly stating there are no side effects or what a failure response looks like, so it is strong but not exhaustive.

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?

Front-loads the purpose, then returns, then usage recommendation, then the parameter default — a sensible ordering with no filler. It is slightly longer than strictly necessary because the return list and the parameter default are stated in separate clauses, 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?

There is no output schema and no annotations, so the description must explain both purpose and returns, which it does by listing the five returned values. Usage context and the default-instance rule are also covered, leaving only failure/error semantics unspecified for a simple connectivity probe.

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 100%, and the single optional 'instance' parameter is fully documented in the schema (name, default, available value demo). The description only restates the default-instance behavior, adding no new syntax or format detail beyond the schema. Baseline 3 applies when the schema does the work.

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 (test GaussDB data source connectivity) and enumerates the concrete return contents: server version, current database, user, read-only status, and latency. This is unmistakably distinct from the schema/query-oriented siblings (describe_table, execute_select, list_schemas, list_tables), which do not probe connectivity.

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?

Gives clear when-to-use context: run at session start or before other tool calls to confirm reachability and read-only transaction enforcement, and use it to diagnose connection, credential, or timeout problems. It also resolves the no-instance case. There is no explicit when-not-to-use or named alternative, but no sibling overlaps in function, so the guidance is effectively complete.

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