pbi_apply_page_spec

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

With no annotations, the description carries the full burden. It discloses transactional atomicity, the four possible outcomes, preservation of page and visual IDs on update, the conservative default of merge mode (to prevent accidental deletion), and that dry_run writes nothing and returns a plan token. It does not mention permissions, conflict handling details, or side effects beyond the core behavior, but overall it is substantially transparent.

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 well-structured with a lead sentence, a clear list of outcomes, and separate paragraphs for page, sync_mode, and dry_run. It is somewhat longer than necessary but every sentence adds value, and code formatting improves readability. It is front-loaded with the primary action and transactional guarantee.

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 complexity (6 parameters, nested spec, multiple modes, and outcomes), the description covers the essential behavioral and workflow context. It explains the dry_run → pbi_apply_plan flow, which is crucial for safe usage. It omits details about seed and request_id, but those are likely auxiliary; an output schema exists, so return values are not needed in the description. Overall, it is sufficiently complete for an agent 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 0%, so the description must compensate. It provides meaningful semantics for page (id or visible name, defaults to spec name, preserves IDs), sync_mode (merge vs replace with conservative default), and dry_run (plan token). However, the central 'spec' parameter is not explained beyond 'el spec', and 'seed' and 'request_id' are completely undefined. While the covered parameters are important, the most critical input lacks any structural guidance.

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 and resource: 'Materializa el spec como una pagina PBIR' (materialize the spec as a PBIR page), and adds a critical qualifier 'en UNA transaccion' (in one transaction). It further distinguishes itself from sibling tools like pbi_create_page_from_spec by listing four explicit outcomes (create, update, no_change, conflict), clarifying that it handles existing pages idempotently.

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 provides clear context for when to use the tool: it applies a page spec to a PBIR page, with outcomes based on existence and change. It gives guidance on sync_mode (merge vs replace) and dry_run, explaining their purposes. However, it does not explicitly name alternative tools or say 'use this instead of X', so it misses the full when-not-to-use clarity.

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