check_ioc_in_baseline

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

Despite no annotations, the description reveals key behavior: it uses a server-side case-insensitive substring search, returns only matching endpoints, and provides observation data including a dashboard_url. It implies read-only operation with no destructive side effects.

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?

Three well-structured sentences: purpose, mechanism, and result presentation instruction with alternative tool. No redundancy, every sentence adds essential information, and the most critical detail (what it does) is front-loaded.

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 no output schema, the description explains what is returned (repos/workflows/runs contacted the endpoint, each with dashboard_url). It also covers both parameters and their purpose. The tool is simple (2 params, no nested objects) and the description is sufficient for an agent to invoke it correctly.

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?

Adds meaning beyond the input schema by explaining that 'owner' is the GitHub org and 'indicator' is a domain or IP substring. Also notes the search is case-insensitive, which is not in the schema. With 100% schema coverage, this extra context is valuable.

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 the Harden-Runner org baseline for domain/IP indicators of compromise. It distinguishes itself from the sibling tool 'find_endpoint_calls_in_tenant' by specifying the scope (single org vs tenant-wide), providing a specific verb and resource.

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 provides an alternative tool ('find_endpoint_calls_in_tenant') for tenant-wide searches, guiding when to use this tool. Also instructs on how to present results with clickable links for each observation, clarifying behavioral expectations.

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