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

readOnlyHint=true already declares it as a safe read, but the description adds value the annotations don't: data is live, rows are positional lists rather than keyed objects, and results may contain sensitive HR data like salary history. It omits any note on result size limits or pagination for large reports, which matters for a tool that returns row sets.

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 sentences, each doing distinct work: what it does and returns, how to get the id, then a sensitivity warning plus endpoint. The core action and return shape are front-loaded with zero filler.

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?

With no output schema, the description appropriately compensates by explaining that the response contains columns and ordered row lists. The main residual gap is the lack of any statement about result volume or limits, which an agent would want before running a large report.

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% and the single parameter is documented only as 'Report id.', so the description's instruction to find the id in the report URL is genuinely additive provenance rather than a restatement. Nothing further is needed for a one-parameter tool, though the id format itself is still not characterized.

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+resource ('Run a saved Namely report by id') and immediately defines the return shape: columns and rows with each row a list in column order. That distinguishes it cleanly from the sibling list_* tools, which enumerate fixed resource types rather than executing saved 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?

Tells the agent the report must be 'saved' and where to obtain the required id (the URL of the report in Namely), which is actionable context. It does not state exclusions or when a sibling such as namely_list_profiles would be preferable for a simple data pull, so it stops short of full when/when-not guidance.

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