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

Annotations already establish read-only, non-destructive, open-world behavior, and the description adds beyond that: an explicit auth-scope requirement (read_heartbeats), a repository-connectivity prerequisite, and pagination. It doesn't describe what a page contains beyond the page cursor, but the added operational constraints are substantive.

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 compact sentences, front-loaded with purpose and payload before the prerequisites and filters. Every clause carries information (repository requirement, filters, paging, scope, endpoint), though the raw endpoint path is the weakest element for an agent choosing a tool.

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 covers the essentials: what is returned (commits plus coding time), the required precondition, auth scope, and paging, with the cursor mechanism handled by the schema's next_page note. Return shape details (fields per commit) remain unspecified but are not blocking.

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 100%, so page, author, branch, and project are all documented in the schema with defaults and constraints. The description's 'Filter by author or branch; paged' only restates that at a high level and adds no name formats or semantics beyond the schema, so the 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?

States a specific verb and resource ('Commits of a WakaTime project') plus the distinguishing payload ('with the time spent coding on each'), which separates it from a plain commit listing. It never names the single-commit sibling wakatime_get_commit, so the plural-vs-singular distinction is left to inference rather than stated.

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 real preconditions for use: a connected repository is required and OAuth tokens need the read_heartbeats scope. It also states the two filter axes (author, branch) and that results are paged. It stops short of naming when to prefer this over wakatime_get_commit for a single commit.

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