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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description usefully adds that no model, draft mutation or human approval is invoked and that pagination continues via nextOffset. This adds context but does not describe the return shape or other operational traits beyond the annotation baseline.

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?

Four sentences, front-loaded with the read purpose, and length is justified by the tool's complexity. Each sentence contributes either scope, pagination, an exclusion, or a side-effect disclaimer, though the 'Continue nextOffset' phrasing is somewhat terse.

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 6-parameter, nested-object read tool with 17% schema coverage and no output schema, the description explains what the brief contains and its side-effect-free nature but does not document the pagination response or the targetKind/limit semantics. Adequate but with clear gaps for the tool's complexity.

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 description coverage is only 17% (essentially just projectId), so the description must carry the load. It adds meaning for offset ('continue nextOffset') and the expected analysis/dossier revision objects ('the same analysis and dossier revisions'), but leaves limit, targetKind, and projectId semantics largely unexplained. Partial compensation for a low-coverage schema.

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 (Read) and resource (a bounded writing brief with questions, form instructions, constraints and revisions), so an agent knows the tool returns a drafting brief. It does not explicitly name which sibling covers the same ground, but the mention of reading supplier evidence 'separately' hints at a boundary. Clear but lacks direct sibling differentiation.

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?

'before drafting in your LLM' states the triggering context, and 'read actual supplier evidence separately' points to an alternative path for compliance checks. It also tells the agent to continue with nextOffset, giving continuation guidance. No explicit when-not condition is given, 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.