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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely non-obvious context the annotations cannot: the 300-event / 90-day hard cap regardless of paging, and the 1-credit cost. It stops short of explaining cursor persistence or cache_max_age behavior.

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?

Four short sentences, no filler, with the core purpose front-loaded before the event list, the cap, the cost, and the parameter rule. Every sentence carries distinct information.

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 4-parameter, no-output-schema read tool, the description covers purpose, limits, cost, and the handle/url choice. The remaining gap is cache_max_age, undocumented in both schema and description, and the absence of sibling routing guidance.

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 75%, so the schema documents url, cursor, and handle reasonably. The description adds real meaning by stating 'Pass either handle or url' — an exclusivity rule the schema does not express, since both are optional with zero required parameters. It says nothing about cache_max_age, the one undocumented field.

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 resource (public activity feed for a user) and enumerates the event types returned (pushes, pull requests, issues, stars, forks, releases), which is concrete. It does not, however, distinguish itself from close siblings such as github_contributions, github_pullRequests, or github_userRepositories, leaving an agent to infer the boundary.

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 'Public events for a user' and the handle/url selector, so the agent can infer the context. But there is no explicit guidance on when to reach for this instead of github_contributions or github_pullRequests, and no note on what happens if both handle and url are omitted.

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