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

Annotations declare destructiveHint=true, openWorldHint=true, and idempotentHint=true, yet the description says nothing about what is destroyed or consumed, that sources are transmitted to an external inference provider (a required consent flag in the schema), or that runs are idempotent and keyed. "Extract ... for human legal review" actively reads as a passive read operation, creating tension with the destructive annotation that the description does not resolve.

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?

A single front-loaded sentence with zero filler; the extraction targets come first. It is efficient, though its brevity is achieved by omitting content rather than by compressing it, which pushes cost onto other dimensions.

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 six-parameter, nested-object, destructive, open-world tool with no output schema, one sentence is far short of adequate. Nothing is said about how prior-run context is sourced, the plain-text-only document requirement, output format, or what the human review handoff looks like.

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 description explains no parameters at all. With 67% schema coverage, the well-documented fields (context, documents, idempotencyKey, consentExternalProcessing) are fine, but the two parameters with no schema description — sourceFields and sourceRunIds — are the non-obvious chaining controls an agent needs explained, and the 75,000-character combined limit is only visible in the schema's object description.

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 ("Extract") with four named extraction targets — obligations, renewal deadlines, service levels, commercial clause concerns — so the agent knows exactly what output this tool produces. However, it does not differentiate itself from adjacent siblings such as xcontracts-summariser, xclause-risk-scoring, or xrenew-radar, which overlap heavily with three of the four named targets.

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?

"for human legal review" hints that the output is advisory and human-in-the-loop, but there is no explicit when-to-use, no exclusions, and no naming of alternatives in a sibling list crowded with contract-analysis tools. An agent choosing between this and xclause-risk-scoring or xcontracts-summariser is given nothing to decide with.

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