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

Annotations declare readOnlyHint=true, openWorldHint=true, destructiveHint=false. The description adds critical behavioral details: orientation is never price-inferred, merged canonicals still resolve with a mergedInto pointer, lineage is append-only with newest first. No contradictions.

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 a single paragraph but is well-structured with clear mode explanations. It is concise given the complexity, though it could be slightly more organized with bullet points. No wasted sentences.

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 (dual mode, merge handling, stable identity), the description covers all essential aspects: listing vs. detail, orientation caveat, merged resolution, lineage format. Output schema exists, so return values need not be described.

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%. The description adds meaning beyond schema: explains that key can be UUID or slug, that limit and cursor apply only in list mode, and that cursor uses previous pagination.nextCursor. It clarifies the behavior of each parameter in context.

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 provides a 'stable cross-venue identity for one real-world question', distinguishing it from venue-specific tools like pm_data_event. It uses specific verbs and resources: 'page the directory', 'resolve', 'track one question across venues'.

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 explains two modes (omit key to list, pass key for full record) and explicitly states when to use: 'Use this to track one question across venues by a durable identity instead of re-matching venue slugs yourself.' It provides clear usage context but lacks explicit 'when not to use' statements.

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