pbi_plan_change

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

Annotations already mark readOnlyHint=true; the description reinforces this with 'sin aplicar nada' and adds concrete behavioral details: the plan includes per-file diff and a state fingerprint, and applying becomes invalid if the project changes. This goes beyond the structured annotations and helps the agent predict side effects.

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, information-dense sentences with no filler. The most important behavior (safe planning, token return) appears first.

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 has an output schema and read-only annotation, the description adds the missing operational context: token semantics, diff/fingerprint contents, and rejection condition. It is sufficient for an agent to decide to invoke it and understand the result.

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 provides only names (`operation`, `arguments`) with no descriptions and 0% coverage. The description compensates by explaining that `operation` comes from `pbi_capabilities.planned_operations` and `arguments` are the same as the target tool would accept, giving the agent enough to construct valid inputs.

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 specific verb phrase 'Calcula un PLAN sin aplicar nada' (calculates a plan without applying anything) and names the return value `plan_token`. This clearly distinguishes it from sibling `pbi_apply_plan`, which actually applies plans.

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 `operation` must be one of those listed by `pbi_capabilities` in `planned_operations`, and `arguments` are the same as the tool would accept. It also implies the typical workflow by explaining that `pbi_apply_plan` rejects the plan if the project changed. However, it does not explicitly state 'use this before applying changes' or list exclusions.

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