list_examples

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

With no annotations, the description carries the burden and does so reasonably: it declares the operation makes no engine call (i.e. no side effects), and discloses the row shape including the 'reference_text' assertion value and resource 'uri'. Pagination, ordering, and error behavior on unknown categories are not covered.

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 purpose sentence, then structured Args and return-row enumeration. The long fixture lists are long but earn their place as the only valid-value documentation; minor redundancy in listing row fields when an output schema exists.

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-param, zero-schema-coverage discovery tool, the description supplies the value domain, the semantic difference between the two filters, the return shape, and the handoff to get_example. Despite an existing output schema, restating the row fields is harmless reinforcement rather than a gap.

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 neither param has an enum, so the description is the only source of meaning — and it supplies it, enumerating 17 valid category fixtures and a set of product endpoints, plus clarifying that product is an alternative filter axis. This is substantial value 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 the vendored engine example requests') and immediately scopes it against the engine-calling siblings with '(no engine call)'. An agent can distinguish this catalog-listing tool from engine_request and get_example 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?

Explicitly frames this as a non-executing listing and names the follow-up tool ('get_example(name) returns the body'), routing the agent from discovery to retrieval. It does not spell out when to prefer list_examples over list_endpoints or list_presets, so full alternatives guidance is absent.

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