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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive, closed-world mutation, so the safety profile is covered. The description adds real value beyond that: the side effect that the service is created in every site language at once, and the dependency on an active Privacy & Cookie Policy. It stops short of saying what happens on repeated invocation (duplicate custom services? same-name collision?), which is the main remaining behavioral gap for an idempotentHint=false create.

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?

Three short sentences, each doing distinct work: definition of the resource, alternative tool, prerequisite. Purpose and the sibling routing are front-loaded, and there is no filler or restatement of the title.

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 14-parameter mutation with a rich, fully-described nested schema and annotations present, the description covers what the schema cannot infer: catalog-vs-custom routing, all-languages creation, and the PCP prerequisite. Since there is no output schema, one could wish for a note on what the call returns or which language codes are validated, but the schema already points to get_site for codes and to MISSING_TRANSLATIONS behavior.

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 all 14 parameters including the nested translations and storage_durations objects are already documented in structured form; the baseline is 3. The description reinforces the multi-language semantics ('created in every site language at once') but adds no syntax, default, or format detail the schema does not already carry.

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 ('Add a fully custom service to a site's privacy & cookie policy') and immediately defines what 'custom' means: 'described in your own words because the catalog does not list it'. It explicitly distinguishes itself from the near-identical sibling create_site_pcp_service, so an agent can disambiguate 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 condition that selects it: 'For a catalog service use create_site_pcp_service instead'. It also states a hard prerequisite — 'Requires an active Privacy & Cookie Policy on the site' — that must hold before calling, which is exactly the kind of when-not guidance agents need for a creation mutation.

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