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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds substantive context beyond that: records are immutable, ordered newest-first, require tickets:read, and reflect review-time interpretation rather than original-capture definitions, which meaningfully shapes how an agent reads results.

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?

Dense and front-loaded: purpose, then ordering, pagination, semantic caveat, and permission in four short sentences with no filler. Only the next_before_id/before_id naming inconsistency slightly muddies an otherwise tight structure.

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?

With no output schema, the description still prepares the agent for return shape (immutable, newest-first, has_more cursor) and adds the permission requirement and interpretation caveat. Combined with read-only annotations, it is close to complete for a simple list tool, missing only explicit alternative routing.

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%, so the description must carry parameter meaning. It explains limit bounds and cursor pagination, but the schema parameter is named 'before_id' while the description says 'next_before_id', a naming mismatch that could confuse an agent about which field to pass. snapshot_id is only implied by 'one owned saved snapshot'.

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 a specific verb and resource (list immutable review records) and scopes it to one owned saved snapshot, with explicit ordering (newest first). It separates the operation from write/read siblings like create_ and export_report_review_envelope reasonably well, but does not name any sibling directly.

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?

Gives usable pagination guidance ('use next_before_id while has_more') and a permission prerequisite, implying the calling context. However it never says when to choose this over get_report_review_envelope or list_report_review_declarations, leaving alternative selection to inference.

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