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

With no annotations, the description carries the full burden and does a fair job: it discloses the returned row fields, the delta categories (grade changes, new/cleared defects, hosts that stopped answering), and that history depth is variable and self-declared via a `sweeps` field rather than fixed. It also signals a paid 'x402'/'we sell' access model, but never states cost, payment flow, or rate limits, and the final sentence is cut off mid-word.

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?

Purpose and scope are front-loaded in the first clause, which is good, but the middle is dense field enumeration and the closing lines drift into sales framing ('we sell the history we have measured'). The text is truncated mid-word ('neve'), leaving the final sentence incomplete and the definition visibly damaged.

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 and no parameters, the description must describe the return shape — it does list row fields and delta types, which is the key coverage. However the truncation removes whatever caveat the last sentence was delivering, and for an x402 paid endpoint the absence of any pricing, payment, or pagination/depth-limit detail leaves a real gap before an agent invokes it.

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?

The tool takes zero parameters, so there is no input semantics to explain and the baseline of 4 applies. The mention of `sweeps` refers to a payload field, not an input, and is not misrepresented as a parameter.

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?

Names a specific resource and scope: the current graded census of the CDP Bazaar index plus the diff against every prior sweep, with concrete row fields (grade, score, live-402 count, defect ids, latency, audited_at). This distinguishes it in substance from the plain 'akari_catalog_report' sibling via the explicit time-series/delta angle, though it never names that sibling to route the agent.

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 only implied through the benefit clause 'so a directory can see what moved instead of guessing' — the agent must infer that this tool is for change-over-time questions and the sibling is for a point-in-time snapshot. No explicit when-to-use, when-not, or named alternative appears anywhere in the text.

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