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

Annotations already declare readOnlyHint=true and destructiveHint=false, yet the description still adds useful context: results are ordered newest first, an owner token is required for auth, and each row carries actor/action/subject/at. It stops short of describing error behavior (e.g. unknown app) or whether the log is truncated.

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?

One front-loaded sentence with the result shape, followed by two short clauses on safety and auth; nothing is wasted and the reader gets purpose before detail.

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 3-parameter read-only tool with no output schema, disclosing the returned fields and ordering covers most of what an agent needs, and limit defaults are in the schema. Only failure modes and log scope remain unstated.

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 67% and documents limit and action, so baseline is 3. The description only implicitly ties 'action' and 'app' to the filter and target, adding no format or semantics beyond what the schema already states.

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 (read the release audit log) and disambiguates the record shape as actor/action/subject/at, so the agent knows exactly what the tool returns. It does not name or contrast a sibling, but no other listed sibling covers audit history, so confusion risk is low.

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 the key prerequisite ('Needs an owner token') and read-only framing, which tells the agent this is a safe read. It never says when to prefer this over other inspection routes or what to do when a token is absent, so usage is only implied.

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