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

Beyond the single readOnlyHint, the description discloses non-trivial behavior: no evidence field accepted from the caller, whole-document refusal with REPORT_RECORD_NOT_RESOLVED on unknown/ambiguous references, honest colour rendering rules, narrative labelled as interpretation rather than evidence, and a signed time-limited download link vs inline base64. Limits (8 sections, 6 records per section) are also stated.

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?

Front-loaded with purpose, then usage, then constraints, then limits. The prose is dense but every sentence carries distinct behavioral information (resolution failure, colour honesty, narrative labelling, delivery modes) with no repetition of the schema.

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 nested, multi-section artifact generator with an output schema, this covers the remaining unknowns: record resolution and failure mode, the no-caller-evidence rule, narrative labelling, and size limits. Nothing an agent needs to call it correctly is missing.

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 3 is the floor, but the description adds genuine semantics: the exact-form requirement for record_id/slug values, the grouping into sections with heading plus optional narrative, and narrative's role as labelled interpretation. delivery's default is restated rather than expanded, keeping it shy of a 5.

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 and output format: 'Create a designed, full-colour Word (.docx) report from Colour Memory records.' This distinguishes it cleanly from near-siblings such as archive_report_brief (brief) and palette_pdf/brand_guideline_pdf, so an agent can select it without opening another 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 names the trigger ('whenever the user asks for a document, report, write-up, handout or Word file built from archive findings') and the alternative to avoid ('instead of writing a plain document yourself'). It also states the precondition that records must come from archive_search or another tool, returned exactly.

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