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

Annotations fully cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description isn't required to restate it. It adds no behavioral context beyond that – no note on automatic pagination behavior, result ordering, or what a 'site assignment' record contains.

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 short sentences, zero filler, with the core action stated first and the filtering options second. Nothing to trim.

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 read-only list tool whose annotations and schema are complete, this is minimally adequate. With no output schema, the description could say what a returned assignment looks like, and given the dense cluster of sibling 'site' list tools it should identify itself more distinctly.

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 100%, so the schema already documents all four parameters including UUID formats and pagination defaults. The description only echoes the two filter parameters and ignores page/per_page, adding negligible meaning. 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?

States a specific verb and resource ('List site assignments for projects'), which is clearer than a bare 'list_project_sites' restatement. However, it does not differentiate from close siblings such as list_project_locations, list_contract_sites, or list_vendor_site_assignments, so an agent can't tell it apart from them without schema inspection.

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?

'Filter by project_id or site_id' implies the intended usage (retrieve assignments scoped to a project or site), but there is no explicit when-to-use, when-not-to-use, or named alternative. The filter hint is the only routing signal.

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