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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description then adds genuinely non-obvious behavioral context: national block counts are deliberately null because that layer is being rebuilt after false positives, and a review object carries the layer's window end as the data date — exactly the kind of caveat that prevents an agent from misreading nulls as missing data.

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 tight sentences, front-loaded with what the tool returns and followed by the null-data caveat. Every clause earns its place — no restatement of the title or name.

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 must describe the return shape, and it does: per-code entries with name and measured-domain count, plus null national counts and a review object with a window end. It stops short of showing the field names or orientation of the response, so an agent still learns the structure only by calling.

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?

Zero parameters, so per the baseline the schema can carry no semantic burden and the description need not document arguments. Nothing is missing on this dimension.

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 resource — a content-category legend mapping codes like NEWS/POLR to human names and measured-domain counts — with the verb implied by 'legend'. An agent can tell this is a static lookup table rather than a filtering or aggregation tool, though it never names the nearest siblings (get_isp_categories, get_category_coverage) to sharpen the boundary.

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: the description makes clear this is the reference for decoding category codes, but it never says when to call it instead of get_censorship_by_category or get_category_coverage, nor any precondition such as 'call this first to interpret codes returned elsewhere'.

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