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

Beyond the readOnly/idempotent annotations, it discloses real behavioral traits: the selection is persisted per connection, no data in Promvia is modified, API-key calls persist nothing and return the siteId, and ambiguous or zero matches return candidates without changing state. That is exactly the stateful context the annotations cannot convey.

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 the purpose, then persistence semantics, then matching behavior; every sentence carries information. Slightly dense with the inline CLI examples, but nothing is redundant.

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 still covers return behavior (siteId under API key, candidate list on ambiguous or no match) and the side effect on subsequent calls, which is everything an agent needs to invoke it correctly.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema lacks: a unique fragment of a name is sufficient, matching is restricted to sites this connection can use, and ambiguous matches yield candidates rather than a failure. This goes past the schema's flat enumeration of accepted forms.

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?

"Choose the site to work on" is a specific verb plus resource, and the description immediately distinguishes this from list_sites (the source of the numbers) and from every site-scoped sibling by explaining that the choice becomes the default for all of them. An agent can tell exactly what this tool does without opening the 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?

It states the trigger (select a site before using other site tools), the lifetime of the effect (until another select_site), and the API-key variant where the caller instead passes the returned siteId. The only gap is that it never mentions the current_site sibling for reading back the active selection.

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