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

Annotations already establish readOnly, idempotent, non-destructive, so the safety profile is covered. The description goes further by disclosing pagination semantics and two response fields (nextAfter, done) despite there being no output schema, which is genuinely additive context.

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 short sentences, front-loaded with the resource, then the continuation contract. No filler and nothing buried.

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 carries the burden of explaining the return shape and does so for the key pagination fields. It stops short of describing log content or chunk format, but the pagination contract is the operationally critical part and it is present.

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 templateId, buildId, and after are all documented in the schema itself; that establishes a baseline of 3. The description restates the role of `after` and links it to nextAfter, adding only marginal meaning beyond the schema.

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 identifies the resource precisely (a page of a build's log) and frames it as a paginated read. It does not, however, differentiate from the sibling get_agent_run_logs, leaving the agent to infer which log source applies.

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?

It gives an explicit driving loop: call again with after = nextAfter until done is true. That is real usage guidance for a paginated tool, but there is no when-to-use / when-not-to-use guidance relative to the alternative log-retrieval tools.

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