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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description still adds substantial context beyond them: hard limits (100,000 lines, 20 MB, 64 KiB per line), per-block pricing with no free tier, ~1 s latency, and a privacy guarantee that submitted text is never logged or stored. It also flags a prompt-injection trust boundary for returned page text and on-chain strings. The only gap is that it doesn't describe the shape of the burst/cohort results, which is partly covered by the output schema.

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?

Front-loaded with purpose and the sibling routing rule, then limits, price, and trust notes in a compact telegraphic style. It is dense but somewhat cluttered with fragments and repeats the line/size limits already present in the schema.

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?

Given a paid, rate-limited analysis tool with an output schema, the description covers everything an agent needs before calling: input format and size caps, cost model, latency, privacy, and the untrusted-data warning. Return-value details are correctly left to the output schema.

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 both `logs` and `origin` are already fully documented in the schema, including that `origin` drives self-referrals and asset links and is never fetched. The description restates rather than extends that information, 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 ('Review supplied web logs') and enumerates the outputs: referrer cohorts, self-referrals, asset links and bursts. It explicitly distinguishes itself from the sibling analyze_agent_traffic by domain (AI client classes and robots rules), so an agent can route without opening either schema.

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?

Names the alternative tool and the exact condition that selects it ('For AI client classes and robots rules use analyze_agent_traffic'), which is the key routing decision among these siblings. Also implies the input precondition (logs must be supplied, no fetching) that gates use.

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