guide

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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, and an output schema exists, so the safety/return burden is light. The description adds no behavioral context beyond the annotations — no mention that the content is static documentation, whether topics overlap, or any constraint on use. This meets the lower annotated bar but adds nothing.

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 with no filler, which is good. However, the long enumeration of topics largely duplicates the enum in the schema while being incomplete, so it spends words on redundant and partially wrong information rather than on what an agent actually needs.

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 one enum parameter, full annotations, and an output schema, the definition is nearly sufficient. The remaining gaps — three valid topics missing from the description and no statement of when the guide should be consulted — are real but modest for a simple documentation lookup 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%, so the description must compensate, but it only partially does: it enumerates 9 of the 12 enum values, omitting 'research', 'report', and 'evaluation'. An agent relying on the prose alone would not know those topics are valid, and no guidance is given on how overlapping topics (workflow vs. research) differ.

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+resource: it returns 'rules and how-to' for a named stage, which distinguishes it from the action siblings (validate_question, fetch_articles, etc.) that perform those stages. The phrasing 'Rules and how-to' makes the retrieval-documentation nature evident, though it never says plainly that it returns instructional text.

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 by 'for a stage' — an agent can infer it should consult this before running a stage, but the description never states when to call it, whether it is mandatory before a stage, or how it relates to concrete siblings such as validate_question or set_screening_criteria.

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