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

Annotations already declare readOnlyHint/idempotent, but the description adds substantial context beyond them: the tool is deterministic with no LLM, it returns documents rather than persisting anything (resolving what the 'write' in the name would otherwise imply), it specifies the output carriers (Markdown, plain text, CSV, JSON rows), and it flags the result as a draft to verify against standards editions in force.

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?

Purpose is front-loaded in the opening clause, but the body is a dense, comma-spliced run-on with long parentheticals ('rodent, termite, UV, cold, oil, watertightness, fire, armour and more...'). Nearly every fact is useful, yet the lack of sentence breaks and ordering makes it harder to scan than it needs to be.

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 9-parameter, nested-object tool with no output schema, the description carries the full return-value burden and does so thoroughly — section-by-section tender ordering, both output formats, and the GTP column semantics. It also points to GET /api/v1/spec/requirements for the option catalogue, closing the only real discovery gap.

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 earns above that by explaining the either/or relationship between sentence, spec, design and cables ('Instead of a sentence / Instead of one cable, a project') and by spelling out what the requirements entries mean for the output — REQUIRED filled with each value's source, OFFERED left blank. It adds the semantic frame the schema can't express, though it doesn't clarify precedence if both sentence and spec are supplied.

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 — 'Write the cable specification for a tender' — and enumerates exactly what comes back: the tender-ordered specification plus the required/offered schedule (GTP). It also distinguishes itself from the sibling design_cable by describing this tool's inputs as 'as design_cable takes it', so an agent knows design_cable produces the design while this turns it into a tender document.

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?

Gives clear context: 'for a tender', one cable or a project of up to 30, and frames the output as 'a draft to check against the editions in force' and 'the same text a Pro member downloads from the designer'. It does not give an explicit when-not-to-use or name a competing sibling for an overlapping case, so it stops short of a 5.

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