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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description still adds value beyond them by naming access conditions (owner account, public document, or valid read link), reiterating that nothing is saved, and disclaiming that it issues no professional opinion. That is meaningful context, but return shape and failure behavior are left to the output schema.

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?

Front-loaded with the non-mutating promise, and every clause carries information about a distinct scenario kind. The trade-off is density: several rules are compressed into telegraphic fragments ('Alternativas se simulan por separado, nunca se suman') that are terse to the point of near-opacity for a model parsing at speed.

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 tool with four polymorphic scenario shapes plus 6 top-level parameters, the description supplies the selection logic, the ID/provenance rules for expected* fields, the access model, and the explicit no-side-effect guarantee, while an output schema handles return values and annotations handle safety. Nothing an agent needs in order to choose a scenario kind and assemble valid inputs is missing.

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 already 100%, yet the description resolves the one ambiguity the schema cannot: 'expectedPrice es el costo del catálogo, no el costo calculado de una matriz', and it explains that matrixCatalogId/itemIndex locate a specific row. It also clarifies that includeConceptEffects adds a per-concept breakdown and that exclude-concepts works on the stated scope. It does not mention dataFingerprint staleness handling or readSharePath usage, which the schema alone must carry.

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?

States a concrete verb and resource ('Calcula una hipótesis') plus the crucial scope limit ('sin modificar ni guardar el presupuesto; funciona sin login'), which immediately separates it from the mutation siblings such as aplicar_edicion_presupuesto. It also enumerates the four scenario shapes the tool handles, so an agent knows exactly what class of computation it gets.

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?

Gives real routing guidance: kind=budget-changes for combined effects, kind=coefficient restricted to a single occurrence and explicitly 'no equivale a editar globalmente su matriz', exclude-concepts for scope exclusions, and 'Alternativas se simulan por separado, nunca se suman'. It also says to use the open budget context. What it never states is the inverse case — when to abandon simulation and call the actual edit tool — so it stops short of full when/when-not coverage.

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