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

Annotations already carry readOnly/idempotent/non-destructive/closed-world, so the description correctly focuses on the things annotations can't express: the large size of full specs (a practical cost signal), which schemas are bundled when operation_id is used, and the output format varying by spec. It stops short of noting anything about auth or versioning of the specs, 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?

Five tight sentences, each earning its place: what it returns, what's available, the preferred targeting mode with its justification, the tag alternative, the default, and the discovery path. The most important guidance (use operation_id) is flagged inline with emphasis rather than 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?

For a 3-parameter read-only fetch with an output schema already describing the returned spec, the description covers everything an agent needs: which spec names exist, how to narrow the response, what happens with no filter, and where to find valid operationIds/tags. No material gap remains.

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 largely does: spec_name's value set is enumerated (banks-connect, ai-connect, pay-connect), tag is defined as 'every operation of one section', and operation_id as 'just that operation with the schemas it references'. It doesn't show string formats/examples for operation_id or tag, instead deferring to the docs page for discovery.

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 ('Get an OpenAPI 3.0 specification for a BANKSapi API') and immediately clarifies the scope variants (full spec, single operation, single tag). It enumerates the three available spec names, so the agent knows exactly what corpus it addresses, and it is clearly distinct from the docs-page/search 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?

Explicitly prescribes the preferred mode ('Pass operation_id ... strongly preferred — the full specs are large'), the fallback ('Pass tag'), and the no-argument default ('With neither, returns the entire spec'). It also names the sibling tool needed for discovery ('fetch the API index via get-banksapi-docs-page'), leaving nothing to inference.

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