pbi_plan_change

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

With no annotations provided, the description carries the full burden. It discloses that the tool does not apply anything (non-destructive), returns a plan_token, includes a per-file diff and a state fingerprint, and that pbi_apply_plan will reject if the project changes. This is valuable behavioral context beyond what an annotation would provide, though it omits error conditions and permissions.

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 concise and front-loaded: the first sentence states the core purpose. Subsequent sentences add essential parameter guidance and behavioral details without redundancy. Every sentence earns its place, and the structure is easy to scan.

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?

Given the tool's moderate complexity (2 params, nested object, output schema), the description covers the essential behavior, parameter sources, and the relationship to pbi_apply_plan. It does not detail the output schema, but that is covered by the output schema itself. It could mention prerequisites like an open project, but the sibling context and this description are sufficient for correct use.

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 has 0% description coverage, but the description compensates by explaining 'operation' as one of the values from pbi_capabilities' planned_operations, and 'arguments' as the same arguments the operation's tool would accept. This adds meaning beyond the bare property names, though it stops short of providing concrete examples or a full enumeration.

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 clearly states the tool 'Calcula un PLAN sin aplicar nada' (calculates a plan without applying anything) and returns a 'plan_token', which is a specific verb and resource. It distinguishes itself from the sibling pbi_apply_plan by explicitly noting it does not apply changes, and from other planning tools by being general-purpose (not just audit fixes).

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?

The description explains the operation parameter comes from pbi_capabilities' 'planned_operations', and that arguments are the same as those for the underlying tool. It also states the plan becomes invalid if the project changes, implying it should be used before pbi_apply_plan. This provides clear context for when to use it, though it doesn't explicitly mention alternatives or exclusions.

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