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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds the stronger, non-obvious guarantee that the code is never executed and that diagnostics include suggested real names for misspelled symbols. It does not describe the shape of the returned report, but the static-analysis behavior is otherwise well disclosed.

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 purpose is front-loaded in the first clause and the diagnostic list is informative rather than padded. The trailing 'Args:' block restates a single obvious parameter, which is mild 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?

With no output schema, the description partially carries the burden by enumerating what the check reports (unknown functions/modules/enum members, bad keyword or positional arguments, arity errors), which is effectively the return content. It stops short of describing the report format or whether results are structured, but it is adequate for a one-parameter, read-only analysis 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% and the single parameter carries only the title 'Code'. The description compensates minimally with 'code: Python source code,' which confirms the input is the snippet to analyze but adds no constraints such as completeness requirements, size limits, or whether imports must be present.

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 ('Statically check Python code that uses CuPy / nvmath-python') and enumerates the exact classes of diagnostics it reports, so the agent knows precisely what the tool produces. It never references the sibling retrieval tools (search_api, get_api_card, get_example), so sibling differentiation is absent.

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: 'without running it' suggests this is the way to validate a snippet before execution or before suggesting it to a user. There is no explicit when-to-use, no when-not-to-use, and no mention of the sibling tools as 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 and openWorldHint=false, so safety is covered. The description goes beyond them by enumerating the payload (exact signature, parameters, return value, pitfalls, GPU-verified example), which tells the agent what a call yields. It does not cover failure behavior for an unknown or ambiguous name.

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 returning-content clause is front-loaded and the whole description is two short sentences plus an args line. The 'Args: name:' block partially restates the schema, a minor redundancy, but it carries the format detail that makes it worthwhile.

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, so the description correctly enumerates what comes back, and the single parameter's expected form is given. Missing only disambiguation from sibling tools and what happens when the name is not found or is ambiguous.

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 0% – the schema only says name is a string. The description compensates by specifying the required format ('Fully qualified dotted name') and supplying a concrete example ('cupyx.scipy.sparse.linalg.cg'), which is exactly the guidance an agent needs to avoid passing a bare symbol.

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+resource: it retrieves an API card containing signature, parameters, return value, pitfalls and a verified example for a single named callable, with a concrete example name. It does not explicitly contrast itself with the siblings search_api/get_example/check_snippet, so an agent must infer that this is the exact-name lookup rather than a fuzzy search.

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 only implied: the example dotted name and the word 'exact' suggest it should be used when the fully qualified symbol is already known. There is no explicit statement of when to use this instead of search_api (unknown name) or get_example (want only an example), and no error/precondition 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 readOnlyHint=true and openWorldHint=false, so safety is covered structurally. The description adds genuine value by disclosing output qualities: the code is runnable, GPU-verified, and includes pitfalls, which is information the annotations do not carry. It doesn't state anything about result size, freshness, or whether the example is unique per call.

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 core capability followed by a concrete example and a compact Args block. The Args restatement of the single parameter is slightly redundant given the schema, but it is short and harmless rather than verbose.

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 single-parameter retrieval tool with no output schema and readOnly annotations, the description covers what is returned (verified example code with pitfalls) and what input is expected, which is sufficient to invoke correctly. Missing only sibling routing guidance, which is a usage-guideline concern rather than a completeness gap in the return contract.

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: it defines task as 'Short description of what the code should do' and supplies a worked example, which is more than the schema's bare string type. The definition is adequate for a single required parameter, though it doesn't state how detailed or keyword-oriented the task string should be.

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 (Get) and a concrete resource (runnable, GPU-verified example code) plus the scope (curated APIs most relevant to a task), with a concrete example. It does not explicitly differentiate itself from the closest sibling check_snippet, which also sounds like code retrieval, 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?

Usage is implied by the example ('matmul with bias and relu epilog') and the phrase 'for a task', which tells the agent the input shape expected. However, there is no explicit when-to-use vs. when-not guidance and no mention of the alternatives search_api, get_api_card, or check_snippet, leaving the routing decision 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 and openWorldHint=false, so the safety profile is covered. The description adds the query semantics and the 1-20 limit bound, but says nothing about ranking behavior, whether results are paginated, or what a result contains, which matters for a search tool with no 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?

The core purpose is front-loaded in the first sentence with examples, and the Args block is compact. The Args section partially duplicates the schema property names, but given 0% schema description coverage it earns its place as the compensating 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?

For a 3-parameter discovery tool with no output schema, the description covers inputs well but leaves the result shape unspecified (names only? signatures? snippets?) and does not indicate the follow-up workflow to get_api_card. It is callable as-is but not fully self-contained.

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, and it does document all three parameters: query as 'what the code needs to do, or part of a function name', library as an optional prefix filter with concrete prefix examples ('cupy', 'cupyx.scipy.sparse', 'nvmath'), and limit as max results 1-20 (a bound the schema does not state). It stops short of describing the matching/ranking semantics that would fully disambiguate vague queries.

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 ('Search CuPy / nvmath-python APIs') and scopes the covered libraries (cuBLAS, cuFFT, cuSOLVER, cuSPARSE, cuDSS, cuTENSOR) with concrete query examples. An agent can distinguish it from get_api_card/get_example by the 'search by task description' framing, though it never explicitly contrasts itself with those siblings.

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 through examples ('batched least squares', 'rfft') and the library-prefix filter, which show the intended input style. However, there is no explicit when-to-use/when-not guidance, e.g. that this is the discovery step before get_api_card, or when to prefer an exact-name lookup over a task-description search.

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