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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds substantial behavioral context beyond those hints: L2 replay is not run unless replay_chain is set, a failed level reports an unsatisfied check rather than upstream semantic truth, a valid signature proves attestation integrity and scope but not semantic truth or currentness, and DataPulse is read-only with no API key and rate limits of roughly one request per second with a small burst. This is rich, non-obvious behavioral disclosure that an agent needs for correct invocation.

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 dense but every sentence earns its place: purpose, scope, exclusions, alternatives, behavioral caveats, and rate limits are all covered. It is somewhat long, but the density of useful routing and behavioral information justifies the length. The most important scoping information is front-loaded in the first sentence, and the rate-limit note is placed at the end where it is still discoverable.

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?

Given the tool's complexity (three verification levels, optional replay, rate limits, and multiple sibling tools), the description is complete. It covers what the tool verifies, what it does not verify, when to use it, when not to use it, the effect of the optional parameter, and operational constraints. The output schema exists, so return values need not be described. An agent has everything needed to select and invoke this tool correctly.

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 100%, so the schema already documents both parameters well. The description adds value by explaining the behavioral consequence of replay_chain (slower L2 daily-head replay to a Git tag, omitted for L1 only) and by clarifying that reference can be a dataset slug or an exact published digest reference. It doesn't add syntax details beyond the schema, but it reinforces the semantic distinction between the two parameters and their runtime effects.

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 opens with a specific verb and resource: 'verify a signed published probe attestation after an evidence audit.' It clearly distinguishes the tool from siblings by naming verify_dataset, verify_evidence, and trust_verdict as alternatives for other verification tasks. The scope of L1/L2/L3 checks is explicitly stated, so an agent can tell exactly what this tool does and what it does not do.

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 description provides explicit when-to-use and when-not-to-use guidance: use it for signed-attestation integrity, not for published receipt verification, live transport comparison, or aggregate verdicts. It also names the alternatives (verify_dataset, verify_evidence, trust_verdict) and gives a recommended deep-audit sequence: search_datasets → get_evidence → verify_evidence → verify_attestation. This is exemplary routing guidance.

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