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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds genuine behavioral context beyond them: LLM gateways are excluded, no model defaults are built in, eligibility is not proof of working generation, discovery is free, and unavailable upstream returns an error. Useful caveats that would otherwise surprise an agent.

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 sentence one, which is good. The following sentences are telegraphic fragments whose referents are unclear ('Candidate eligibility does not prove successful real generation'), costing more parsing effort than the words save.

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 the description covers the important ambient facts: exclusions, no built-in defaults, deferred loading, error behavior. Slightly short of complete because it never routes the agent to get_model_schema for the detail it says loads on lookup.

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 enum parameters are documented in-schema, so the baseline is 3. The description mentions attachment_fields/result_codec but adds nothing about category or media_type semantics, so it does not exceed the schema's own detail.

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: reads the public task_api index and its default tool-to-model bindings. This is distinguishable from get_model_schema (schema lookup) and the generate_* siblings, though the description never names the sibling that returns detail so the split is only implied.

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?

Implies this is discovery-only ('candidate eligibility does not prove successful real generation') and hints that detail lives elsewhere ('modes and attachment_fields/result_codec load on schema lookup'), but never explicitly says to call get_model_schema for full detail. No explicit when-not or prerequisite statements.

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