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

With no annotations, the description carries the full burden and does so thoroughly: it discloses cache behavior (returns free if already generated), cost (1 AI bridge, plus a paid action consuming plan quota and MCP action), monthly caps, and a pointer to get_usage. This goes well beyond a minimal mutation warning.

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?

The description is front-loaded with the core purpose and every sentence carries operational detail. However, the cost information is split across two sentences with some redundancy ('consuma 1 ponte AI' and 'AZIONE A PAGAMENTO: consuma 1 unità... e 1 azione MCP'), making it slightly denser than necessary.

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 3-parameter tool with no output schema and no annotations, the description covers output form, parameter domain, caching, and billing comprehensively. It leaves project_id's role implicit and does not specify exactly what 'anchor' means, but the essential invocation context is well covered.

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 schema already describes source and target as URLs. The description adds that source/target may also be node-ids, that they refer to pages from the last audit, and that the intended relationship is pillar→orphan. project_id is not elaborated, and with 67% schema coverage the description partially compensates but leaves one parameter reliant on schema-only context.

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 opens with a concrete verb ('Genera') and a specific resource ('ponte semantico' paragraph with anchor), then defines the exact use case: linking a target page from a source page, explicitly identified as the pillar→orphan pair of the Action Plan. This clearly distinguishes it from the many getter and analysis sibling tools.

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 provides clear context for when the tool applies (pillar→orphan pairs from the last audit) and directs the agent to get_usage for remaining credits. It does not explicitly name alternative tools or state when not to use it, though the cache-free note implies a decision point.

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