harbor_search

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

With no annotations, the description bears full burden. It reasonably discloses the tool's behavior: it returns top matches with session, date, role, and snippet. It mentions the dependency on harbor_ingest, but could further clarify what happens if no data is indexed (e.g., empty results).

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 description is concise at two sentences, front-loading the purpose. Every sentence adds value. Could be slightly more structured (e.g., separate prerequisite note), but overall efficient.

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?

Given the simple tool with an output schema, the description covers the main functionality and return fields. It does not discuss edge cases, pagination, or ordering of results, but is adequate for a search tool with clear scope.

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 should fully explain parameters. However, it does not elaborate on the 'query' or 'k' parameters beyond their names. The description mentions 'top matches' which weakly hints at 'k', but provides no guidance on format or behavior.

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 description clearly states the tool searches indexed Claude history for past work, specifying the verb 'search' and the resource 'indexed Claude history'. It mentions returning top matches with details, but does not explicitly differentiate from the sibling tool 'harbor_stats', which could be another retrieval tool.

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?

The description provides clear usage context: use to find past work by query. It includes a crucial prerequisite: 'Run harbor_ingest first', which guides the agent on correct sequencing. However, it does not specify when not to use this tool or suggest alternatives among siblings.

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