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

Beyond the readOnlyHint annotation, the description discloses the countRead opt-in mechanism, independence from read list permissions, the exact error condition (collection_count_forbidden), and the return shape. This is rich behavioral context far exceeding the annotations.

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 three sentences and front-loaded with the core purpose. While dense, it includes relevant behavioral details like opt-in gating and error semantics. Minor extras like 'spec B4, issue #1056' add reference context but are not strictly necessary, so not a perfect 5.

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?

Despite having no output schema, the description explicitly states the return value. It covers permission gating, error cases, and the precise collection scope semantics. For a tool with nuanced authorization behavior, this is thorough and complete.

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%, and the parameter descriptions are already clear ('The app id.', 'The collection name declared in the app's manifest'). The tool description adds no extra semantics beyond what the schema provides, so baseline 3 applies.

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 identifies the tool as returning 'the live row count of a v2 app's collection' and distinguishes it from list/get operations by emphasizing 'no filter and no paging' and returning '{ count }'. This separates it from sibling tools like list_rows and get_row.

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 provides clear context on when to use (whole-scope count) and describes the countRead opt-in gating, but does not explicitly name alternative tools. The phrase 'no filter and no paging' implies when it's appropriate, and the '3 spots left' shape gives a concrete use case.

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