sketch_dimension_set

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

With no annotations present, the description carries the full burden and does so well: it discloses atomicity ('all or nothing', earlier updates rolled back), the re-solve side effect of changing a dimension, and the staleness contract for profile refs. This is the behavioral context an agent cannot get from the 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 purpose, then atomicity, then value semantics, then return shape, then an example. Every block earns its place; the line break formatting is slightly dense but no sentence is redundant.

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?

A mutation tool with neither annotations nor an output schema, so the description correctly spells out the return shape ({dimensions, status, profiles}) and the rollback guarantee. Minor gaps remain: no guidance on combining driven with value, or on the updates list limits.

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 67%, and the description compensates by explaining value typing (number = mm/degrees, string = expression) and by naming the driven state and parameter_name fields in the opening line. It omits return_profiles, which the schema documents, and says nothing about the 500-item cap on updates.

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 specific verb and resource ('Change existing dimensions') plus the fields that can change (value/expression, driven state, parameter name), which implicitly separates it from the sibling sketch_dimension (creation). It never names that sibling explicitly, so an agent must infer the create-vs-modify split.

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?

Tells the agent this is for existing dimensions only, and gives operational guidance for the edge case where a feature reports ENTITY_NOT_FOUND (re-read with sketch_profiles(contains=...)). No explicit 'use X instead' routing to a sibling for creation, which is the only real gap.

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