Build a client report

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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the mutation profile is known. The description adds genuinely new behavioral context: the build is asynchronous ('takes a moment') and results must be fetched via get_report. It does not say what create_report itself returns (job handle?) or what happens if a report already exists, which is why it is not a 5.

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 with zero waste; the core action and formats are front-loaded, and the sequencing constraint follows immediately. Every clause carries information.

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?

No output schema exists, and the description implies the result is retrieved later via get_report rather than returned inline, which is the key thing an agent needs. The one remaining ambiguity is what create_report itself returns (a job/status object?), but the essential calling pattern is complete for a 2-parameter tool.

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 50%: project_id is documented in the schema, and the format enum has no schema description. The description compensates partially by spelling out 'PDF or XLSX', mapping directly to the enum values, but adds nothing about project_id or format defaults. Baseline 3 fits given the partial gap.

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 (builds) and resource (PDF/XLSX report of a project) with the branding qualifier, and names the follow-up sibling get_report, so the agent can distinguish it from retrieval tools without opening any schema.

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 prescribes the workflow: build first, then call get_report, which tells the agent this is not a synchronous 'get the report' call. It stops short of naming when to prefer create_report over alternatives like preview_launch or save_report_file, so no exclusions are given.

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