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

Adds substantial context beyond the annotations: a hard cost of $0.02 USDC per request, an x402 payment requirement, a warning that returned URLs are untrusted, and an explicit statement of what the output is not. Annotations cover read/write and openness hints, but pricing and trust posture are only in the description.

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?

Six short sentences, zero waste, and the core capability plus scope are front-loaded ahead of cost and trust caveats. The only noise is the 'FetchDelta:' prefix, which is minor.

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 single-parameter tool with no output schema, the description covers cost, auth, scope, output nature and trust caveats. It does not describe return shape or error behavior, which keeps it short of fully complete, but nothing critical for invocation is missing.

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 description coverage is 0% and the single parameter is undocumented in the schema, so the description must carry the load. It conveys cardinality (one to five pages) and multi-value semantics, but does so by saying to 'repeat the url query parameter' while the schema defines an array named 'urls' — a naming/shape mismatch that could mislead an agent.

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: extract price mentions, commercial terms and source Markdown from public pricing pages, with an explicit scope cap of one to five pages. The negative framing ('not verified prices or normalized plan comparisons') implicitly separates it from catalog/diff-style siblings without naming them, which is why this stops short of 5.

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 scope limit ('public pricing pages') and the exclusion ('Text evidence, not verified prices or normalized plan comparisons') imply when this tool is and isn't appropriate. However, no sibling is named and no explicit condition routes the agent between pricing_snapshot and preview_page, resolve or catalog.

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