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 read-only behavior, semantic vs full-text mode, pagination, sorting, filtering, and the return shape. Minor gaps remain around error behavior and index freshness, but these are not critical for correct invocation.

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 opens with purpose and read-only status, then delivers a tightly formatted arg list where every line adds value. No filler or repetition; the length is justified by 11 undocumented parameters.

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?

For a complex 11-parameter tool with no output schema and no annotations, the description is thorough: it covers all parameters, return keys, mode selection, and alternatives. It could add more detail about hit shapes or error cases, but the agent can invoke correctly from this definition.

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 fully compensates. Every parameter is explained with syntax details, defaults, examples, and even the instance source. This goes far beyond the schema's bare names and types.

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?

Description states a specific verb and resource: full-text or semantic search across the Gramps tree, read-only. It distinguishes itself from manage_<type> tools by explicitly saying those are for known handles or raw object data.

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?

Explicitly says to use manage_<type> with get/filter when you already know the handle or want raw object data, which is a clear when-not-to-use condition. The description also frames the tool as type-ahead style search across the index, making its intended context obvious.

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