search_directory

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

Discloses it returns up to 10 matches with name and handle, but does not mention behavior for empty term or the refresh parameter. Without annotations, more detail on side effects or auth would help.

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, efficiently describes action and output with 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?

Covers core functionality but lacks details on refresh parameter, search semantics (case sensitivity, partial matches), and output format beyond name/handle.

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?

With 0% schema coverage, description partially explains 'term' (name/handle) but omits 'refresh' entirely, failing to compensate for the lack of documentation.

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 HackerOne's public program directory by name/handle term, which distinguishes it from siblings like list_programs and search_disclosed_reports.

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?

Implied usage for searching programs by name/handle, but no explicit guidance on when to use this tool over siblings like search_disclosed_reports or list_programs.

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