search

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

Without annotations, the description provides useful behavioral context: fuzzy, ranked, criteria. But lacks details on pagination, empty results, or result format.

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?

Two sentences, front-loaded with scope, then ranking criteria, then usage hint. No wasted words.

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?

The description explains scope and ranking but omits output format or any warnings. For a search tool, return structure would be helpful, especially without output schema.

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 100%, so description doesn't need to repeat param details. It adds overall context (ranking) but no per-param improvements. Baseline 3 is appropriate.

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 verb 'search' and the resources 'projects, tasks, sessions, and notes'. It distinguishes from sibling tools (CRUD operations) by being a broad recall 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 suggests using it to 'recall anything in the workspace', implying a recall context. However, it does not explicitly exclude cases where a specific tool (e.g., project_list) would be better.

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