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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context: access depends on the owner account, a public document, or a valid read link; it does not save changes or emit a professional opinion; and 'pending' signals unresolved pages, branches and detail. That is meaningful beyond the annotations, though a large share of the text describes return-field semantics rather than behavior.

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 two operating modes are front-loaded, which is good, but the remainder is a single dense block of jargon-heavy sentences with no paragraphing or list structure. Nearly every sentence carries information, yet many decode output fields (cells, differentFields, sharedBasics, presentation, pending) that the existing output schema could carry, making it hard to scan under time pressure.

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 dual-mode, batch-capable tool with comparison logic, the definition covers access requirements, null-vs-zero semantics, row explosion limits and provenance source fields, which is close to complete. Minor gaps remain, such as the absence of an explicit statement of what happens when expectedDataFingerprint is stale.

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 description coverage is 100%, so parameters such as expectedDataFingerprint, version and readSharePath are already documented in the schema. The description adds value mainly for compare ('alinea filas por catalogId y omite rows de las cabeceras') and for the batch row limits. It does not explain parameters the schema omits, and forConcept is discussed as returned data rather than as an input, so the baseline 3 holds.

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 the verb and resource in both operating modes: 'Con conceptoId devuelve el APU detallado, sus diez insumos principales y los pasos del PU' and 'Con conceptoIds y la huella vigente devuelve cabeceras y hasta 20 filas directas por APU'. It also explicitly separates itself from siblings, routing usos/incidencia to consultar_usos_insumos and branch expansion to inspeccionar_componentes_apu, so an agent can distinguish it without opening schemas.

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 definition gives per-mode guidance (single conceptoId vs batch conceptoIds with fingerprint) and names two alternatives with their conditions. It also warns 'El lote no acredita cobertura completa', which shapes how results should be trusted. It lacks an explicit negative case stating what this tool should never be used for, so it stops short of 5.

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