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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: what each output row represents and the special 'spec'/'length_m' fields, which is what an agent needs to interpret results. It does not mention performance or limits, but for a pure computation that is minor.

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?

Front-loaded with the verb and resource, then the output composition, then the routing sentence. The enumeration of row types is dense but each element carries information an agent needs; no filler sentences. Slightly long, but appropriately sized for the detail conveyed.

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?

With an output schema present, the description need not restate the full return contract, and it still explains the semantic meaning of the rows (manufacturer/part number, spec, length_m). Parameter, annotation, and output coverage are all adequate; only edge cases like malformed documents are unaddressed.

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% and the 'document' parameter is fully documented in the schema (JSON object or JSON text, as returned by get_example/apply_patch/normalize, file path accepted locally). The description only says 'from its document' and adds no syntax or format detail beyond the schema, so the baseline of 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 and resource ('Compute the bill of materials ... of an electrical installation from its document') and describes the exact output shape in domain terms (one row per manufacturer/part number, spec, length_m). It also contrasts itself with the sibling 'wiring', so the agent can distinguish the two without opening schemas.

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?

Explicitly states the use case ('Use it to prepare a quote or an order') and names the alternative sibling ('wiring gives the wire list and cable schedule'), which tells the agent which tool produces what. It lacks an explicit when-not condition or prerequisites, but the routing guidance is clear.

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