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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's contribution is the return shape: client, line items with taxes, subtotal, discount, tax, total, deposit, expiry, approval status, signature date, and client link. That is meaningful added context because no output schema exists. It stops short of saying whether missing/unsigned values are null or absent.

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 first sentence ('Full estimate: client, line items, tax, discount, deposit, expiry, approval and signature') is a fragment that the second sentence then restates in near-identical terms, creating redundancy. The field enumeration is useful given no output schema, but the front-loading could be tighter.

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 simple single-record read with one fully specified parameter and rich annotations, the description supplies the missing piece — the return contents — and places the call in a workflow. Only edge behavior (unknown id, missing signature) is left unstated, which is minor for this 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?

The single parameter is fully documented in the schema (type, pattern, and 'From list_estimates'), so the schema carries the burden. The description adds no format, id-source, or error semantics beyond what the schema and annotations already provide.

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 uses a specific verb+resource ('Returns one estimate') and scopes it to a single full record with its client and line items, which implicitly separates it from list_estimates and get_client. It never names a sibling explicitly, so differentiation is inferable rather than stated.

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?

'Read it before changing or sending the estimate' gives concrete workflow context that points an agent toward update_estimate/send_estimate after this call, and the schema note 'From list_estimates' shows how to obtain the id. There is no explicit when-not-to-use guidance or mention of alternate lookups.

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