opencdr_reviews_read

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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description still adds real value with the pagination rule ('Follow next_after even for an empty page'), the owner-grant filtering scope, and the warning that a decision neither mutates nor authorizes a queued job. It says nothing about what a 'binding' contains or how results are ordered or truncated.

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 front-loaded with the core action and uses short sentence fragments, each carrying distinct information: scope, filter, pagination, semantics of decisions, and authority mode. Slight density and terminology ('binding', 'Fleet authority') that is never unpacked keep it from being maximally clear.

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?

For a three-parameter read tool with no output schema and no parameter descriptions, the definition covers pagination and the two authority modes reasonably well, but it never describes the shape of the returned inbox entries or the 'binding' object, which an agent needs since no output schema exists. The fleet-versus-core sentence also assumes familiarity with those deployment terms.

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 carry parameter meaning. It does explain cursor mechanics ('Follow next_after even for an empty page') and hints that filtering is grant-based, but it never explains the relationship between the `after` request field and the `next_after` response field, nor what `limit` controls, nor when to supply `approval_id` versus omitting it. Partial compensation for a low-coverage schema.

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 opens with a specific verb and resource: 'Read the owner-scoped approval inbox or one exact review and its binding,' which tells an agent it handles both a collection and a single-item lookup. It does not name a sibling, but it does draw the read/decision line ('A registry decision does not execute a mutation'), which helps separate it from review-execution tools.

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?

Usage is implied by 'owner-scoped approval inbox or one exact review' and reinforced by 'Current owner grants filter results,' so an agent can infer it reads approval state visible to the caller. There is no explicit when-not-to-use guidance and no named alternative to route to for decisions or execution, leaving selection to inference.

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