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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context on top: it supplies evidence only, never saves/approves, explains the absence semantics ('if a concession... is absent, it is not approved'), and warns about pagination before claiming a complete audit. Return-pagination behavior is a genuinely useful disclosure not present in the annotations.

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 lead sentence is front-loaded and the pagination warning is well-placed at the end. But the middle sentences are repetitive, particularly 'If no extra concession is approved, the result says so', which restates the prior sentence's logic with no added 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?

An output schema exists, so return-value structure need not be described. The description adequately covers the read-only contract and pagination caveat, but leaves the two required parameters undocumented, which is a substantive gap for a tool whose central input is the proposed text being audited.

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 0%, so the description must compensate for three parameters. It only addresses 'offset' indirectly via 'Page with offset', and says nothing about accountId (a required UUID) or proposedText (a required 1-12000 char string). The most important input – the text being audited – is left completely unexplained.

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 description says it will 'Show the locked approved record' and describe 'what the assistant must not add or discount', which conveys a read-only audit of approved constraints. However, the verb+resource relationship is fuzzy: it never states that it audits the supplied proposedText against the approved record, so an agent cannot fully predict the output from the name plus description. Siblings like get_approved_context are not differentiated.

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?

'This tool supplies evidence; it does not save or approve anything' implicitly separates it from write siblings such as create_account or record_renewal_offer, and 'Page with offset before claiming a complete audit' gives a concrete usage condition. But there is no explicit statement of when to choose this over get_approved_context or search_approved_terms, so guidance is implied rather than stated.

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