Conferir conexão SitePerto

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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint. Beyond that, the description adds a genuine data-boundary disclosure: it reads only the key-linked project and explicitly not clients, forms, payments, or other projects' content. That is real behavioral context about access limits. It stops short of explaining the temporary-key auth mechanism or the response shape.

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, zero filler, with the positive scope stated first and the exclusions second. Nothing is repeated from the name or 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 parameterless read tool with no output schema, the description covers scope well but never describes what comes back (connection state, project info) or how errors surface. Since no output schema exists, that return-value context would have been the description's job to carry.

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 nothing to document and no schema gap to compensate for. Baseline 4 applies; the description offers no parameter detail because none is needed.

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?

The description states a specific read action and, crucially, its scope: it only consults the project tied to the temporary key. This lets an agent separate it from siblings like inspect_site and send_draft. However, it never says what the tool actually returns (connection status, project metadata), which the name connection_info implies but the text leaves implicit.

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 implicitly frames when the tool is appropriate by declaring its narrow scope, and the exclusions hint at when NOT to rely on it for other data. But no alternative tool is named and no explicit condition selecting this over inspect_site is given.

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