curator_verify_lesson

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

Goes well beyond the annotations: server stamps the check time, reaudits replace the same claim record (consistent with idempotentHint=true), and a changed source invalidates other results built on the older revision — a consequential side effect the agent could not infer. It also clarifies that this only records supplied evidence rather than fetching/certifying.

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 action and its scope, then prerequisites, inputs, statuses, and side effects in a logical order. Every line carries information; the only cost is that the dense line-wrapped fragments require careful reading.

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?

An output schema exists so return values needn't be covered, and the mutation/idempotency semantics are well explained. Minor gap: source_url is required while source_text is optional, and the description doesn't clarify that source_url is still required when hashing supplied text.

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 0%, so the description must compensate, and it does for the hard cases: source_revision (official revision/ETag) vs source_text (checked text, hashed server-side), and the three status values verified/contradicted/unsubstantiated, which no enum in the schema conveys. slug, source_url and lesson_revision remain unexplained beyond their names.

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 + resource: 'Record a protected lesson's factual freshness' with an explicit scope exclusion ('without editing its text'), which cleanly separates it from siblings like lesson_patch, lesson_append and lesson_remove. It also implicitly contrasts with the read-only lesson_verifications tool.

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?

Provides a concrete workflow ('Read lesson_verifications for the lesson revision', then check the exact claim against an official HTTPS page) and states the operation's boundary ('it does not fetch or certify a URL'). It stops short of naming explicit when-not-to-use cases or contrasting with lesson_patch by name.

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