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

The description adds substantial behavior beyond annotations: it never refetches, never decides whether a change occurred, discards uncertain or inconsistent claims, and is model-backed and rate limited per credential. Annotations indicate read-only and non-destructive, and the description confirms and expands on this with specific operational details.

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?

The description is front-loaded with the core purpose and then packs every sentence with relevant details: input requirements, output structure, uncertainty handling, edge cases, and cost/rate limits. No fluff or repetition detracts from its informativeness.

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 thoroughly covers what to expect: classified changes (price, plan, discount, availability, packaging), quoted before/after evidence, rejected claims with reasons, INSUFFICIENT_EVIDENCE for non-commercial pages, and the caveat that commercial intelligence is not guaranteed. This fully equips the agent to decide when and how to invoke 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 the baseline is 3, but the description adds useful context: targetId comes from observe_public_page, and fromObservationId/toObservationId represent before/after observations. This links the parameters to the intended workflow beyond what the schema's one-line descriptions offer.

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 clearly states the tool's function: semantic interpretation over pricing/commercial-offer pages, classifying proven commercial changes. It explicitly distinguishes from the sibling observe_public_page by noting it never refetches and requires prior observations.

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?

It gives explicit preconditions: requires a target with two persisted observations and a CONTENT_CHANGED verdict. It also tells when not to expect useful output (non-commercial pages return INSUFFICIENT_EVIDENCE) and references the companion tool observe_public_page for obtaining targetId.

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