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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, but the description adds materially richer behavioral detail: it never raises a protocol error on invalid input, instead returning a structured {'error': ...} object, and it explicitly says the call is safe to retry after corrections. This goes well beyond the annotation hints and sets clear expectations about failure modes.

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 front-loaded with a clear one-sentence summary followed by a concrete example, usage guidance, and error behavior. It is longer than average but every section earns its place. The 'FREE.' fragment is extraneous and the output example is slightly verbose, preventing a perfect score.

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 tool with nested object parameters and an existing output schema, the description covers virtually everything an agent needs: input shape, example output, recommended use, exclusions, error contract, and retry safety. The presence of an output schema means the return format does not need further detail, and the description still provides a sample.

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%, so the baseline is 3. The description adds value by showing a concrete typical input/output pair that ties 'deadlines' to rows from compute_deadlines and clarifies the expected shape of 'now'. The error example also adds a semantic constraint ('non-empty list of rows from compute_deadlines') not present in the schema, nudging this above baseline.

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 opening sentence states a specific verb ('Mark') on a specific resource ('each computed deadline') with concrete statuses ('open, due soon, overdue or submitted'). It clearly distinguishes the tool from compute_deadlines by saying 'Not for computing the deadlines themselves,' so an agent can tell it apart from sibling tools without ambiguity.

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 explicit recommended contexts ('Use when polling an incident timeline or deciding what to escalate next') and an explicit exclusion ('Not for computing the deadlines themselves'), effectively routing the agent away from compute_deadlines/compute_deadlines_multi. This is direct when-to-use guidance with alternative tools implicitly identified.

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