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

Beyond readOnlyHint/destructiveHint it discloses non-obvious behavior: every document appears exactly once, first-page snapshot_count is the exact total, cursors expire after 24h with a cursor_expired error, and no content is returned regardless of detail. That is genuinely useful context the annotations cannot carry. It loses a point for leaving truncation/limit behavior and the cold/archived inclusion defaults undiscussed.

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?

It is front-loaded and dense with no filler sentences; each clause carries operational meaning. The telegraphic style is efficient but occasionally cryptic — 'Legacy sort=updated_desc|updated_asc keeps the 3.2.1 listing' and the bare 'tainted' field assume context the reader may not have.

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?

Pagination, ordering, and cursor lifetime are fully specified, and the presence of an output schema excuses it from explaining return shapes. But a 17-parameter listing tool with zero schema coverage leaves too many filters unexplained (filters, include_cold, include_archived, date bounds, verification_status, review_verdict) for an agent to call it confidently in filtered scenarios.

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 0% across 17 parameters, so the description must carry the load, and it covers detail, fields, order, cursor, sort, and the include_unverified/include_tainted toggles well. However, limit, filters (an open-ended object), include_cold, include_archived, updated_after/updated_before, verification_status, review_verdict, namespace, and tainted receive no explanation at all, which is a large gap for a tool this wide.

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 opening sentence names a specific verb and resource ('cursor-paginated census of documents') and immediately excludes a competing interpretation ('not ranked, no vectors'), which separates it from sibling search-style tools like recall_document and query_workspace. An agent knows exactly what class of operation this is before reading the schema.

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 concrete selection rules for its own modes: order is 'the default under API 2026-11', sort is the 'legacy 3.2.1 listing', and detail=summary applies 'when fields is not given'. It also states cursor reuse conditions and that next_cursor=null means done. What it never does is name a sibling to use instead when ranked/vector search is actually wanted, so the exclusion stays implicit.

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