replay_search

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

With no annotations, the description carries the full burden. It discloses useful behavior: results are scoped to 'this account', returned as short cards with named fields, and the stored values are anonymised into blank slots. It is silent on pagination, result caps, and whether either filter is required, which an agent would want before calling.

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?

Three sentences with the core definition front-loaded, then filtering options, then the next-step pointer. The parenthetical explanation of 'replays' earns its space because the term is domain-specific; no sentence is filler.

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 no output schema and no annotations, the description appropriately names the card fields and the follow-up tool, so an agent knows what comes back and what to do with a code. Remaining gaps are result limits and filter-combination semantics, both minor for a search tool with two optional parameters.

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 coverage is 0%, so the description has to compensate, and it largely does: 'query' is explained as words matched against the title, and 'topic' is given meaning plus concrete examples (version-control, testing, databases). It still doesn't say whether the two filters are ANDed or how partial matches behave.

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 ('Find replays') and goes further by defining the domain term ('routines that worked in real sessions, with the values we can recognise turned into blank slots'). It enumerates the returned card fields, which makes the tool's output shape unmistakable and clearly separates it from replay_get.

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?

Explains the two narrowing options ('words in the title' vs 'by a topic') and explicitly routes the agent onward: 'Call replay_get with a code for the steps.' That names the alternative and the condition selecting it, but there is no guidance on when not to search, or how the two filters combine.

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