Search Users

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

Beyond the readOnlyHint and openWorldHint annotations, the description reveals a key behavioral nuance: the return is a dict with 'sections (name -> raw text)' and the LLM must parse the raw text to extract users and profiles. This alerts the agent to expect non-structured output requiring interpretation, which is valuable and non-obvious.

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 brief and front-loaded with the purpose. The Args/Returns structure is clean and scannable. The only issue is the extraneous 'ctx' line, which adds noise; otherwise the description is appropriately sized and well-organized.

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 simple search tool with only two schema parameters, readOnly/openWorld annotations, and an output schema, the description covers the essential invocation details and return format. It explains the need to parse raw text, which is critical context. The lack of usage alternatives is a gap, but the description still feels complete for the tool's complexity.

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 must compensate. It does define query with concrete examples and max_results with a default. However, it also lists 'ctx' as an arg, which is absent from the input schema and excluded by additionalProperties: false. This could lead the agent to pass an invalid parameter, undermining trust in the parameter 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 opens with 'Search for Instagram users.', clearly stating the verb and resource. It distinguishes from search_locations by resource type, though it doesn't explicitly state whether search matches usernames, full names, or both. Example queries ('john doe', 'photographer') imply free-text search, which helps clarify scope.

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 gives no guidance on when to use this tool versus alternatives like get_user_profile or search_locations. There is no mention of preferred contexts, exclusions, or contrasting sibling tools. The agent gets no help deciding between searching and directly fetching a known user.

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