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

Beyond the readOnly/idempotent/closed-world annotations, it discloses non-obvious behavior: overloaded names return every overload, call_template uses a ? marker per parameter, and procedures (CALL) plus SQL-data-modifying functions cannot be run via execute_query, with note explaining why. That is substantive operating context the annotations do not provide.

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 dense but front-loaded, leading with what it returns before qualifying details. Each clause carries information, though the return-value enumeration is partly redundant given the output schema.

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 3-parameter read tool with an output schema, the description covers everything an agent needs: source catalog, overload semantics, execution eligibility, and default-schema fallback. Nothing required for correct invocation 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 100%, so the baseline is 3, but the description adds meaning: the name/specific_name mutual-exclusion rule is restated and default-schema fallback is confirmed. It does not add format or syntax detail beyond that.

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 opens with a specific verb and resource tied to a concrete source (QSYS2.SYSPARMS) and enumerates exactly what is described: parameter mode/type/default, scalar return value, and table-function result columns. This clearly separates it from describe_table and list_routines.

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 when the overload behavior applies ('An overloaded name returns every overload unless specific_name picks one') and routes execution decisions to callable_with_execute_query, naming execute_query as the related sibling. It stops short of explicitly saying to call list_routines first to obtain a specific_name, though the schema hints at 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 declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description usefully adds the default-schema fallback and the fact that CCSID metadata is included, but says nothing about failure modes (e.g., unknown table/schema) or result shape, and an output schema exists anyway.

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?

Two front-loaded sentences with no filler: the purpose and returned attributes come first, then the schema-default caveat. Slightly list-heavy, but every clause carries 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 two-parameter read tool with full schema coverage, an output schema, and annotations covering the safety profile, the definition is nearly complete. It could still note that the table must already exist or how a missing schema resolves, but no critical invocation detail 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 description coverage is 100% and both parameters (table, schema) are already documented in the schema, including the same default-schema note. The description adds no format, qualification, or naming-convention detail beyond what the structured fields provide, so baseline 3 applies.

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 ('Get') and resource ('detailed column information for a specific table') and enumerates the returned attributes (data types, lengths, nullability, defaults, CCSID), which clearly separates it from siblings like list_tables, get_object_ddl, or get_table_constraints.

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 the use case (inspecting one table's column structure) but never states when to prefer this over get_object_ddl, search_columns, or list_tables, nor any conditions or exclusions. The only guidance given is the default-schema fallback behavior.

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 structurally. The description adds two useful behavioral facts beyond the annotations: the SELECT-only security restriction and that result sets are capped by default. It does not disclose the actual default limit value, failure behavior, or timeout characteristics.

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?

Three short sentences, front-loaded with the core action and immediately followed by the key constraint. Every sentence carries information, though the final sentence is slightly redundant with the limit parameter already described in the schema.

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. However, for a query-execution tool surrounded by validate_query and schema-introspection siblings, the description omits error-handling expectations and any guidance on validating queries first, leaving minor gaps for correct invocation in a workflow.

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 sql, limit, and params are already documented in the schema, which sets the baseline at 3. The description adds only marginal meaning for 'limit' by noting results are limited by default, but it does not explain parameter binding syntax for 'params' or the practical impact of the default cap.

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 SQL SELECT query against the IBM Db2i database'), making the operation instantly recognizable. It does not, however, explicitly distinguish itself from the sibling validate_query, which an agent might reasonably consider for the same SQL text.

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 implies usage through the constraint 'Only SELECT statements are allowed for security,' which tells the agent this is for querying rather than DDL/DML. There is no explicit when-to-use clause and no mention of when to prefer validate_query, list_tables, or search_tables instead.

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 safety (readOnly, idempotent, non-destructive). The description adds genuinely useful behavior beyond them: the MCP_CUSTOM_TOOLS data source, fuzzy fallback on unknown entity names, and the empty-result fallback that lists loaded entity names. It does not cover output shape, but an output schema exists.

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 what is returned, then filtering, then edge-case behavior. It is information-dense and every sentence carries weight, though the first sentence is a long run-on list that could be tightened slightly.

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, return values need not be described, and the description covers source, filtering, and fallback behavior adequately for a 2-param read-only lookup. Only the explicit sibling-routing guidance 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 100%, so the baseline is 3, but the description earns extra credit by explaining the interaction between the two params: filter by either entity or table, omit both to return everything, and unknown entity names trigger partial matching rather than failure.

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 (List) and enumerates the resource types returned: business entities, row filters, table/column descriptions, and non-FK relations. The phrase 'relations that the catalog does not declare as foreign keys' implicitly distinguishes it from get_table_constraints, though it does not name that sibling outright.

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 implied rather than stated — 'row filters most queries need' hints it belongs in query-construction workflows, and the filter/omit semantics are explained. But it never says when to prefer this over describe_table, get_table_constraints, or get_related_objects, so the agent must infer the boundary.

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 it as a safe, idempotent read (readOnlyHint, idempotentHint, destructiveHint: false, openWorldHint: false). The description adds valuable context beyond that: it explains the computed 'needs_attention' flag, what conditions set it, and why it matters (journal-based replication). It also notes the OS version requirement, which is a meaningful operational constraint.

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?

Three sentences, front-loaded with the core purpose. Every sentence earns its place: the first describes the output, the second explains the needs_attention flag, and the third states the version requirement. No redundancy.

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. Annotations cover the safety profile. The description provides the necessary domain context (what needs_attention means, replication use case, IBM i version) and the underlying API, making it 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 100%, so the schema fully documents the three parameters (limit, filter, schema). The description adds no parameter-level syntax or format details. Baseline 3 is appropriate when the schema does the heavy lifting.

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 the physical data files... with their journal...'. It names the underlying IBM i API (QSYS2.OBJECT_STATISTICS) and the exact fields returned. It doesn't explicitly differentiate from siblings like list_tables or describe_table, but the domain specificity is high.

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 explains the semantics of needs_attention and its relevance to 'journal-based replication tools', which implies a use case. However, it doesn't state when to use this tool versus alternatives like list_tables or describe_table, nor does it mention exclusions or prerequisites beyond the OS 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/idempotentHint/destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: the output is DDL only and is not executed, and it carries a platform version requirement (IBM i 7.3+).

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?

Three short, front-loaded sentences with no filler. The core action comes first, then the non-execution caveat, then the version requirement.

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. The description supplies the mechanism and version prerequisite; only the routing against sibling tools is absent, which is a minor gap for this fairly self-contained 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%, with an enum on 'type' and clear text on 'object' and 'schema', so the schema does the heavy lifting. The description adds no parameter detail (e.g., format of 'object', qualified name handling), matching the baseline 3 when coverage is complete.

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: return the SQL DDL that recreates a database object, and names the underlying mechanism (QSYS2.GENERATE_SQL). This is clearly distinct from metadata-oriented siblings like describe_table, though no sibling is named explicitly to sharpen the contrast.

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 implies usage via a behavioral caveat ('Does not run the generated statements') and a version prerequisite ('Requires IBM i 7.3 or later'), but never states when to choose this over describe_table or execute_query, nor any explicit exclusions. Adequate context, but no alternative 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 cover readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds a genuine constraint beyond them: availability is gated by IBM i release/TR level (7.3 TR9, 7.4 TR3 or later), which an agent must know before calling. It stops short of noting ordering or result 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?

Two sentences with zero filler; the core capability is front-loaded and the prerequisite trails it. Every clause carries information an 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 values need no explanation, and annotations carry the safety profile. Together with the stated prerequisite, the definition gives an agent everything needed to decide and call correctly for a two-parameter read 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 coverage is 100%, so both parameters are already documented, including the defaulting behavior for 'schema'. The description adds no syntax, naming, or qualification detail beyond the schema, so the baseline 3 applies.

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 (List) plus the exact resource (views, indexes, triggers, and other dependent objects) and the underlying system function (SYSTOOLS.RELATED_OBJECTS). The dependency framing ('objects that depend on a table') clearly distinguishes it from siblings like list_views, list_indexes, and get_table_constraints.

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 'depend on a table' phrasing implies the use case (reverse dependency lookup rather than plain listing), and the stated OS release prerequisites are a real usage condition. However, it never says when to prefer this over list_views/list_indexes/get_table_constraints, and gives no exclusions or alternatives.

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, openWorldHint=false, and destructiveHint=false, so the safety profile is fully covered by structured data. The only extra behavioral fact the description offers, the default-schema fallback, is duplicated verbatim in the schema, and there is no output schema explanation needed since one exists. A 3 reflects modest added value over 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?

Two short sentences, front-loaded with the core action and the return contents, with the schema-default caveat last. No filler or redundancy beyond the minor overlap with the schema text.

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 annotations covering safety, an output schema covering return values, and 100% schema description coverage on both parameters, the description is sufficient for correct invocation. The only omission is disambiguation from sibling metadata tools, which keeps it from a 5.

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 ('table' and 'schema') are fully documented in the schema. The description's mention of the default schema fallback restates the schema's own wording rather than adding format, casing, or qualification semantics. Baseline 3 is appropriate.

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 uses a specific verb and resource ('Get all constraints ... for a specific table') and enumerates the constraint types returned (primary keys, foreign keys, unique constraints), so an agent knows exactly what this returns. It does not differentiate itself from adjacent siblings like list_indexes or describe_table, which also expose table metadata, 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?

There is no explicit when-to-use guidance, no prerequisites, and no named alternative. The implied context (you need constraint metadata for one table) is inferable from the sibling list, but the description itself does not route the agent between get_table_constraints, describe_table, and list_indexes.

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 readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses row-merging behavior with summed counts, sort order (mti_used then times_advised), CREATE INDEX column ordering with possible DESC suffix, local-time semantics for last_advised/since, and the explicit constraint that no indexes are created. This is exactly the behavioral context an agent needs.

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, then ordered into aggregation, sorting, column format, time semantics, and the read-only guarantee. Dense but every sentence adds distinct information; only the time-zone sentence is arguably redundant with the schema.

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, return values need not be explained, yet the description still usefully characterizes the shape of results (merged rows, reason codes, sort order) and the read-only scope. Scope, filters, and interpretation are covered; only explicit sibling routing 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 description coverage is 100%, so all four parameters are already documented in the schema, including the local-time format for 'since' and the limit cap. The description's remark that last_advised and since are in system local time largely restates the schema, adding no syntax or format detail beyond it, so the baseline 3 applies.

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 the indexes the query optimizer asked for... from the IBM i index advisor (QSYS2.SYSIXADV)') and distinguishes itself from siblings like list_indexes by making clear this is advisor output, not actual index definitions. An agent can tell exactly what it returns 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?

Usage is implied rather than stated: the tool is for inspecting optimizer advice before creating indexes, and the description helps interpret results ('advice where the optimizer kept building and reusing an MTI is the strongest signal'). However, it never names an alternative sibling (e.g. list_indexes) or an explicit when-not condition, so routing guidance is left 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=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only what the listing contains (uniqueness, column info), which is largely redundant with the existing output schema.

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?

Two short sentences, front-loaded with the core action. Nothing is padded or repeated, and the secondary default-schema note is appropriately placed at the end.

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 read-only listing tool with full annotation coverage, a complete output schema, and fully documented parameters, the description is essentially sufficient. It omits any hint about result size or indexing edge cases, but nothing required to invoke it 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 description coverage is 100%, so both parameters are already documented in the schema. The description's note about the default schema duplicates the schema text for the 'schema' parameter and adds no new syntax or format detail, so the baseline 3 applies.

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 all indexes for a specific table') plus the scope of returned fields (uniqueness, column information). It is clearly distinct from siblings like describe_table or get_table_constraints, though it does not name an alternative 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?

The description never says when to prefer this tool over siblings such as get_table_constraints or describe_table, nor does it give any exclusions. The only conditional statement concerns the optional schema parameter's default, which is usage of a parameter rather than guidance on tool selection.

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 safety is covered. Beyond that, the description adds real behavioral detail: it documents the deduplication semantics for overloads and enumerates the returned attributes (type, language, external program, SQL data access, result sets, text). It omits the limit/QUERY_MAX_LIMIT behavior, leaving that to the schema.

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 purpose and the source view, then the dedup rule and the routing hint. The column enumeration in sentence two is somewhat list-heavy but still informative rather than filler. No wasted preamble.

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 further explanation, and annotations carry the safety profile. Combined with the schema's full parameter documentation, the description supplies everything an agent needs to select and call this tool 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 100%, so the schema already documents type, limit, filter, and schema thoroughly. The description restates only the default-schema behavior, adding no syntax or filter-format guidance beyond what the schema provides. Baseline 3 is appropriate.

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 ('List SQL procedures and functions in a library') and anchors it to its source (QSYS2.SYSROUTINES), with the notable qualifier 'one row per specific routine, so overloads appear once each'. That granularity lets an agent distinguish it from list_tables, list_views, and describe_routine without opening a 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 explicitly routes complementary work elsewhere: 'Use describe_routine for parameters and a call template', which tells the agent when this tool is insufficient. It also clarifies the default-schema fallback. It does not, however, state exclusions or contrast against sibling listing tools such as search_ibmi_services.

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 and repeatability profile is fully covered by structured data. The description adds the (libraries) terminology mapping, which is useful context, but nothing about result scope or limits beyond what annotations provide. With annotations carrying the 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?

Two sentences, zero waste, and the core action is front-loaded before the optional filter detail. Every clause earns 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?

For a zero-required-parameter listing tool with rich annotations and an output schema, the description covers purpose, scope, and the only parameter's behavior. Nothing an agent needs to call it 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 description coverage is 100% and the filter parameter is fully documented in the schema, including the wildcard syntax and an example. The description restates the wildcard behavior in one clause without adding format or edge-case detail beyond the schema. Baseline 3 is correct when the schema does the heavy lifting.

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 (List) and resource (schemas/libraries) in a named database, and the parenthetical 'libraries' disambiguates the Db2 for i terminology. An agent can distinguish this from list_tables or list_views 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?

The optional filter usage is stated ('Optionally filter by name pattern'), which implies when the parameter applies, but there is no explicit when-to-use versus siblings or when-not-to-use guidance. For an inventory-listing tool the usage context is largely self-evident, so this is adequate but not rich.

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. The description's only added behavioral fact is the default-schema fallback; it says nothing about empty results, case sensitivity of the wildcard, or limits, so it adds modest value only.

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?

Three short sentences, front-loaded with the primary action and scope. Slight redundancy with the schema text on the wildcard and default schema, but overall efficient and easy to scan.

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 and full annotation coverage, the description need not explain return values, and it adequately covers invocation for a two-optional-param list tool. The only gap is disambiguation from search_tables, which is a routing concern the description should have closed.

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 100%, so both parameters (filter, schema) are already documented in the schema, including the wildcard example and default behavior. The description merely restates that the filter uses * and that schema defaults, adding no new syntax or constraint beyond 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?

States a specific verb and resource (list tables) with scope (in a schema/library) and the default-schema fallback. However, it does not differentiate itself from the sibling search_tables, which also filters tables by name pattern, so an agent cannot cleanly choose between them from this 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?

It mentions that the default schema is used when none is supplied, which is helpful context, but gives no explicit when-to-use guidance and no exclusion or alternative pointing toward search_tables, list_schemas, or describe_table. The overlap with search_tables is left unresolved.

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 that an unspecified schema falls back to a system default and that the filter supports wildcards, but discloses nothing beyond that (e.g. result cap or ordering).

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?

Two tight sentences with the core action front-loaded; nothing is wasted. The default-schema and wildcard details are secondary but relevant, so minor trimming room remains rather than excess.

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 both optional parameters are fully documented. For a simple read-only list tool with annotations covering safety, this is essentially complete, with only cross-tool routing left unaddressed.

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 description restates the wildcard filter and default-schema behavior rather than adding new format or constraint details, so the baseline of 3 applies.

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 all views in a schema (library)' — so an agent knows exactly what object type is returned. It does not explicitly distinguish itself from siblings like list_tables or list_schemas, but the resource noun makes the separation obvious from name 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?

Usage is implied (call it to enumerate views) but there is no explicit when-to-use guidance or routing to an alternative. It also never says when not to use it, e.g. versus search_tables or describe_table, so the agent must infer the boundary.

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 establish this is a safe, idempotent read, and the description layers on substantial extra context: the source system tables, that low/high are the second-lowest/second-highest values, that unstatted columns report source "none", that masked columns return counts but no values, and the compute row-scan cost. These are exactly the non-obvious behaviors an agent needs before invoking.

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?

Three dense sentences, each carrying distinct information (what is profiled, default source, compute opt-in, masking). It is front-loaded with the deliverable and wastes little, though the second sentence is long and packs several ideas that could be split for faster scanning.

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 explain return values, and it instead covers the behavioral gaps: data sources, stats staleness semantics, masking, and compute limits. For a profiling tool with subtle stat-based defaults, nothing an agent needs to call it 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 100%, so the baseline is 3, but the description adds meaning the schema does not: compute's 20-column ceiling, that the default column set is every column vs. the first 20 under compute, and the masking behavior that affects which parameters yield values. It stops short of documenting the schema parameter's fallback beyond what the schema already says.

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 opens with a specific verb+resource ("Profile a table for ETL work") and enumerates exactly what is produced: row count, deleted rows, size, last change, and per-column distinct/null/low/high values. This is far more informative than a tautology, though it never names or contrasts itself with the closest sibling, describe_table, which an agent may consider a substitute.

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 clearly states the default behavior (stats from SYSCOLUMNSTAT) and the condition that changes it ("Set compute to true to scan the table for exact numbers"), including the cost tradeoff ("Slower on large tables") and the 20-column cap. There is no explicit when-not or named alternative, but the context for choosing compute is unambiguous.

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 readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds non-obvious scoping behavior — allowlist narrowing and implicit system-library exclusion — which an agent could not infer from the annotations or schema.

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?

Four tight sentences, front-loaded with the core action and matching fields, then the scoping rules. No filler, though the allowlist/system behavior is stated twice in compressed form and could be slightly tighter.

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. The description covers matching semantics, wildcard, default scope, and allowlist behavior — everything needed to call this 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 coverage is 100%, so every parameter is already documented in the schema, including wildcard usage and the include_system/allowlist interaction. The description largely restates this, adding little syntax or format detail beyond the schema, so the baseline of 3 is appropriate.

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 (find/search) and resource (columns) plus the matching fields (COLUMN_NAME, SYSTEM_COLUMN_NAME, COLUMN_TEXT) and the cross-library scope. This clearly separates it from the sibling search_tables, which an agent could otherwise confuse with a table lookup.

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 concrete operating context: wildcard syntax, the allowlist constraint, and the default of skipping Q*/SYS* libraries unless include_system is true. It does not explicitly name a sibling alternative or say when NOT to use it, but the conditions for correct use are clear.

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 and destructiveHint false, but the description adds that the tool only reads the catalog and explains downstream authority and schema constraints when running returned examples via execute_query. It also notes that table functions must be qualified, which is useful behavioral context beyond 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?

The description front-loads the core purpose, then layers in usage guidance, fallback behavior, and caveats. It is dense and mostly earns its sentences, though the downstream execute_query and qualification details make it longer than strictly necessary for a search 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 the description need not explain return values. It covers the catalog source, the included metadata, the zero-argument behavior, and relevant caveats for using the returned examples, making it complete for an agent to call the tool 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 100%, so the input schema already documents all five parameters in detail. The description adds only a small amount of parameter-interaction context, such as what happens with no query and no category, which does not materially exceed the schema baseline.

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: 'Find IBM i SQL services (views, table functions, procedures, and more...)' in the named catalog QSYS2.SERVICES_INFO. It also clarifies the context of use before writing SQL that uses an IBM i service, which helps distinguish it from generic query or metadata 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?

Gives clear when-to-use guidance: call it before writing SQL that uses an IBM i service instead of guessing names and parameters. It also describes the no-argument fallback behavior. It does not name alternative sibling tools for related metadata searches, so it stops short of full when-not/alternatives coverage.

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 covered. The description adds genuinely new behavioral context: the schema allowlist restricts which libraries are searched, and Q*/SYS* libraries are skipped by default — scope behavior the annotations cannot convey.

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?

Three front-loaded sentences with no filler: purpose, match targets, then wildcard syntax and scope rules. Dense and efficient, though the scope sentence could be tightened.

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 adequately covers search scope and system-library handling. The only real gap is the missing routing against list_tables, which leaves a sibling-selection ambiguity for the 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 100%, so all four parameters are already documented in the schema, including wildcard syntax and the include_system interdependency. The description restates the allowlist/system rules without adding syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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 clear verb+resource ('Find tables') and names the specific match surfaces (TABLE_NAME, SYSTEM_TABLE_NAME, TABLE_TEXT), which is more precise than the name alone. It does not explicitly distinguish itself from the close sibling list_tables, so an agent must infer that this is the filtered variant.

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 explains search scope behavior (allowlist, system-library skipping) which implies when results are constrained, but it never says when to prefer this over list_tables or search_columns. Usage is inferable rather than 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?

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds meaningful mechanics beyond that: parsing via QSYS2.PARSE_STATEMENT, catalog resolution of tables/columns/routines, and that read-only and schema-allowlist findings 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?

Two tight sentences, front-loaded with the core action and the non-execution guarantee before the implementation detail. Every clause earns its place with no redundancy.

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 unnecessary, and the description covers the action, the mechanism, the checks performed, and the non-execution guarantee. Nothing an agent needs to call it 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?

With a single parameter at 100% schema description coverage, the schema already carries the semantics. The description reinforces that the statement is not executed, which mirrors the schema text rather than adding new meaning, so the baseline 3 applies.

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 ('Check a SQL statement') plus the crucial scoping constraint 'without running it', and explains the mechanism (QSYS2.PARSE_STATEMENT plus catalog existence checks). This clearly separates it from the sibling execute_query, which actually runs SQL.

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?

'without running it' implicitly tells the agent to use this before execute_query, and the enumeration of checks makes the intended use case clear. It stops short of explicitly naming execute_query as the alternative or stating when validation is mandatory, so it is clear context rather than full routing guidance.

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