get_repository_report

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

With no annotations, the description carries the full load, and it does disclose two non-obvious behaviors: results include acceptable and unscored functions (coverage), and the snapshot ID pins a consistent view across pages. It omits ordering of results, whether the operation is read-only, and what a returned entry contains, which are meaningful gaps for a paginated data tool.

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?

Two sentences with no filler, and the inclusion scope is front-loaded before the pagination instruction. The second sentence is slightly compressed ('Pass the first snapshot ID' assumes the agent already knows the ID comes from page one), but nothing is wasted.

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, no annotations, four parameters at 0% description coverage, and one parameter with an unusable schema — for that complexity the description should say what an assessed-function entry contains and what the snapshot field is returned as. It covers pagination consistency but leaves the agent guessing about return shape and about the project parameter.

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 compensate. It does explain the most critical parameter well — snapshot is a consistency token taken from the first page — and the word 'Page' implies limit/offset semantics, but the 'project' parameter (schema is an opaque `not: {}` with no type) is left entirely unexplained in both schema and description.

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 says it pages through 'all assessed functions, including acceptable and unscored ones,' which conveys an enumeration resource, but it never mentions 'repository' or 'report' — the actual name — so the mapping between the tool name and the described behavior takes a moment of inference. It also does not name any sibling (analyze_function_health, scan_repository_hotspots, review_changes) to differentiate scope.

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?

The only procedural guidance is pagination-related ('Pass the first snapshot ID on subsequent pages'), which is a mechanic rather than a when-to-use rule. There is no statement of when this enumeration should be preferred over analyze_function_health or scan_repository_hotspots, and no prerequisites or exclusions.

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