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

Beyond the read-only/idempotent annotations, the description discloses TTL provenance (minepoa /api/params pending_ttl_epochs; segments.json for archived segments), fallback behavior (16 flagged via ttl_flags Stale/Unconfirmed), the ttl_observed cross-check, estab_ttl, and an important limitation: counts only, never a pending score or seal.

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?

Purpose is front-loaded, but the description is two long, heavily nested sentences packing field definitions, TTL source logic, flags, and a CSV endpoint. The content is mostly relevant, yet the run-on structure with many parentheticals makes it hard to parse.

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?

No output schema exists, so the description must explain return content; it lists the cohort fields and explains TTL provenance, fallback flags, cross-checks, and the counts-only limitation. It is sufficient for a read-only query, though it does not describe the overall response shape beyond the field list.

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%, including enum meanings for dir and sort and a detailed segment note. The description adds no parameter-specific meaning beyond incidentally mentioning 'segment', so the schema carries this dimension.

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 it reports the pending expiry horizon per pending cohort in a segment and enumerates the returned measures (pending, no_seal, expires_close, closes_left, expires_est_ts, watched). It also gives a clear use statement, 'Use it to see when each pending cohort expires and which TTL value that rests on,' but does not explicitly distinguish it from sibling tools such as get_pending_by_epoch.

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 clear use context: seeing when each pending cohort expires and which TTL value supports that estimate. It does not state when not to use it or name alternatives, so the agent must infer the choice against get_pending_by_epoch.

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