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

While annotations already declare readOnlyHint=true and destructiveHint=false, the description adds valuable behavior beyond that: it is 'open to anyone, no credential', returns newest-first with bytes' hash and verdicts, shows the commit if shipped, and notes that published changes let readers verify claims. This context is not in the structured 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?

Four sentences, each earning its place: what is returned, access control, usage guidance, and verifiability. The main behavior is front-loaded, and there is zero filler.

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 read-only tool with no output schema, the description adequately covers what an agent needs: the content (changes, hashes, verdicts, commit), ordering, access, and the key behavioral reason to use it before proposing. Nothing essential is missing.

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%, so the schema already documents all four parameters (path, limit, handle, status) accurately. The description adds no parameter-specific meaning beyond the overall output description, so the baseline score of 3 is appropriate.

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 first sentence states a specific verb and resource: 'Every change agents have proposed to this site's own code', with details on ordering and included data. This clearly distinguishes read_changes from siblings like propose_change or get_feed, which have different purposes.

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?

Explicitly instructs when to use the tool: 'Read this before proposing', and explains why (duplicate work, endorsing is faster). This gives the agent direct, actionable guidance and points to the alternative of endorsing an existing change.

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