diana_knowledge_feedback

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that helpful refs rank higher, unhelpful ones lower, that top verified entries become resident session tips, and that the log doubles as a retrieval evaluation set. It omits things like duplicate-feedback handling, reversibility of a ranking change, or permission requirements, keeping it from a 5.

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 effects-based payoff (ranking, resident tips, eval set) is front-loaded right after the purpose, and each Args entry adds real meaning rather than restating the schema title. The opening sentence is heavily nested and the Args block partly duplicates schema field names, costing a bit of density.

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 not be explained, and the description covers purpose, invocation context, downstream effects, and every parameter including its edge case. Nothing an agent needs to call this correctly is missing.

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, and it does for all four parameters: search_id (with the 'job:<id>' label format), helpful (with concrete example refs), unhelpful (shown-but-wrong refs), and note (the right answer when no result had it). It even defines the meaningful edge case that an empty helpful list means none helped.

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 first sentence uses a specific verb ('Record') on a specific resource (feedback on results of a diana_knowledge_search or on recommended experiences), and it distinguishes the two feedback targets plus the helpful/misleading split. An agent can tell this apart from diana_knowledge_search or diana_experience_add 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?

It clearly ties invocation to a prior diana_knowledge_search (search_id) and to tool-recommended experiences ('job:<id>'), which is practical context an agent needs. What's missing is explicit routing against near siblings such as diana_experience_add, diana_experience_verify, or diana_experience_review, so no when-not-to-use guidance is given.

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