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

Goes well beyond the readOnly/idempotent/openWorld annotations: it discloses that extraction is LLM-based, that it 'decides nothing', that unreadable and uncertain values are surfaced separately, and that page/row provenance is attached. One tension it does not address is how an LLM read squares with the idempotentHint, since repeat calls may yield different readings.

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, and the long field enumeration is dense rather than padded. It still runs three heavy sentences, and phrases like 'the values that could not be read and the ones the reader is unsure of' could be tightened.

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 no output schema, the description carries the full burden and does: it enumerates the returned constructions, their provenance fields, uncertainty reporting, and the optional embedded rule-engine verdict with clause and source. An agent knows what comes back and what to do with it.

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%, so all four parameters are already documented in the schema. The description reinforces `url`, `text` and the effect of `standard`, but adds no syntax or edge-case guidance for `hint` and nothing beyond what the schema says about 'auto' resolution, so 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?

Specific verb (read/extract) plus resource (power cable datasheet) plus the exact output shape (constructions with sizes, layers, thicknesses, screen/armour, diameters, standards). It also names the downstream consumer check_cable / POST /api/v1/check, which separates it from the design and lookup siblings.

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 accepted input forms (maker PDF, https link, pasted datasheet or tender text) and routes the agent: set `standard` to have rows checked in the same call instead of a separate check_cable round trip. It adds the caution to review values before relying on a verdict, but gives no explicit 'do not use this for X' exclusion.

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