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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description adds that PK/FK/comment metadata is returned, but says nothing about permissions, visibility of system schemas, or behavior on an unknown table name, so it only modestly exceeds 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?

Two short sentences, zero filler, with the returned metadata front-loaded and the usage cue trailing. 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?

With no output schema, the description must convey the return shape, and it does by enumerating the returned metadata. It is complete for a single-parameter introspection tool, with only minor gaps such as error behavior for non-existent tables.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents 'table' including the ERP.ITEMS qualified-name form. The description's 'table or view' phrasing mirrors rather than extends 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 concrete verb ('Show') and a precisely enumerated resource: columns, data types, comments, primary key and foreign keys of a table or view. An agent can distinguish this from list_tables or run_query by the metadata it returns, though the description never names those 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?

'Use it before writing SQL' gives clear situational guidance that implicitly routes the agent away from run_query when it lacks schema knowledge. It stops short of explicit when-not conditions or naming the alternative tool, so it falls just under a 5.

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, and closed-world, so the safety profile is covered. The description adds useful domain context (these are curated, pre-approved PL/SQL procedures returning SYS_REFCURSOR), but says nothing about result volume, pagination, or catalog size.

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 identifies the resource and its nature with no filler. Nothing is redundant or buried.

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, the description carries the burden of explaining what comes back. It does state that reports and their parameters are returned, but gives no sense of the return shape, pagination, or how the listed parameters should be used when calling run_report.

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 takes zero parameters, so the baseline is 4. The mention of 'their parameters' correctly signals that parameter metadata is part of the returned payload rather than something the caller supplies.

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 (curated, pre-approved ERP reports) and adds the technical nature of those reports (PL/SQL procedures returning SYS_REFCURSOR), which is more than a tautology. It implicitly contrasts with run_report, but never names any sibling to differentiate 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 alternatives are named despite run_report being an obvious next step after discovery. The intended workflow (discover then run) is left entirely 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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds only that results include business descriptions; it says nothing about result size, pagination, or how many tables are typically returned.

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 sentence, front-loaded with the verb and resource, with zero filler. Nothing is repeated from the title or 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 no output schema, the description usefully signals the return content ('tables and views... with their business descriptions'), and annotations carry the safety profile. It is nearly complete for a simple zero-required-param listing tool, lacking only a note on result scale.

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% and the single 'filter' parameter is fully documented in the schema as a case-insensitive substring match. The description adds no syntax or format detail beyond that, 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?

The description names a specific verb and resource ('List tables and views in the ERP schema') plus a scope detail ('with their business descriptions'), so the agent knows exactly what is returned. It does not explicitly distinguish itself from siblings like describe_table or list_reports, which is the only 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?

There is no guidance on when to use this versus describe_table (for column-level detail) or run_query, and no mention of prerequisites or when-not-to-use. Usage is only implied by the word 'List'.

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, so safety is largely covered. The description adds genuinely non-duplicative behavior: a hard 200-row return cap, JSON output, and an enumerated rejection list (DDL/DML, PL/SQL, DB links, DBMS_/UTL_) that the annotations do not convey. It stops short of covering errors, timeouts, or multi-statement handling.

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 filler, with the core action and result limit front-loaded before the constraint list. Every clause carries information an agent can act on.

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-only query tool with no output schema, the description covers invocation scope, the dangerous/rejected cases, the return format, and the size ceiling. Nothing essential to calling 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 restatement of the 200-row maximum and the single-statement constraint adds no syntax or format meaning beyond those schema descriptions, 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 (Execute) plus the exact resource class (a single Oracle SELECT/WITH statement) and the result contract (at most 200 rows as JSON). This is clearly distinguishable from siblings like run_report, list_tables, and describe_table, which are report/catalog oriented rather than free-form 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?

Gives explicit when-not guidance: data-changing statements, PL/SQL, DB links and DBMS_/UTL_ packages are rejected, which tells the agent when this tool will fail. It does not, however, say when to prefer run_report over run_query or mention any other alternative, so the routing guidance is one-sided.

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 a closed world, so the safety profile is fully covered by structured data. The description adds no behavioral context of its own: no note on cost/latency of running a report, no indication of what happens if the name is unknown, and no mention of result size behavior despite the max_rows cap.

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, zero filler, with the action stated first and the discovery prerequisite second. Nothing could be removed without losing 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 simple read-only tool with no output schema, the description covers the core invocation path, but the undocumented max_rows parameter and the absence of any hint about the returned result shape leave gaps. It is adequate rather than 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 coverage is 67%: name and params are documented in the schema, but max_rows has no description anywhere. The description adds one genuinely useful pointer — that report parameters are report-specific and discoverable via list_reports — but it does not explain max_rows or the params format beyond what the schema already gives.

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 ('Run a curated report by name'), which is precise enough to separate it from the ad-hoc run_query sibling. It does not explicitly contrast itself with run_query, so the agent must infer that 'curated' means pre-defined rather than arbitrary 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?

Explicitly directs the agent to list_reports as the discovery step for both report names and their parameters, which is the key prerequisite for calling this tool. It gives no exclusion guidance (e.g. when to prefer run_query instead), but the positive workflow is clear.

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