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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the response includes the invoice's lines and names the underlying endpoint (GET /invoice/details), but says nothing about auth, error cases, or pagination – adequate against the lowered bar.

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?

Two terse fragments with zero waste and the key scoping detail (lookup keys, included lines) front-loaded. Slightly telegraphic, but every element earns its place.

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 tool with a complete two-parameter schema and full annotation coverage, the description supplies what is needed: what it fetches, how to identify it, and that lines are included. No output schema exists, so return detail is only lightly sketched.

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% with self-documenting fields ('by' enum and 'value'). The description's 'id, reference or number' merely echoes the enum values already in the schema, adding no syntax or format detail beyond it; baseline 3 applies.

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 (get) and resource (invoice) and adds scope: lookup by id, reference, or number, returning lines. This clearly distinguishes it from the sibling synchroteam_list_invoices, which returns multiple invoices.

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?

The phrase 'One invoice' implies single-record retrieval versus the list alternative, but no explicit when-to-use, when-not-to-use, or named alternative is given. Usage is inferable but not spelled out.

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