Set Project Preferences

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful non-annotation context: partial-merge behavior, the per-section {ok, value} | {error} return contract, read-only fields (dataSafety), and the Teamwork reservation requirement.

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-loads the verb and the partial-update constraint, then examples, then return contract and prerequisites. Dense but every sentence carries information; the inline examples are long but high-value for a deeply nested 11-parameter schema.

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 destructive, 11-parameter, deeply nested mutation tool with no output schema, the definition covers scope, prerequisites, read-before-write guidance, return shape, read-only fields, and Teamwork constraints. Nothing essential to calling it correctly 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 description coverage is 100%, so the baseline is 3, but the description goes beyond it by supplying four concrete payload examples (workingUnits, dimensions, floorPlanCutPlane, environment) that show the nested object shape an agent must construct. It doesn't enumerate every section, but the examples materially reduce invocation error.

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 ('Changes Project Preferences') and immediately clarifies scope with 'only the given sections/fields', which distinguishes a partial-update semantics tool from a full replacement. It also names the sibling get_preferences as the companion read tool, so an agent can place it precisely.

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?

Explicitly instructs to 'read the current values with get_preferences first' and states the Teamwork prerequisite that Project Preferences must be reserved. This is strong when-to-use and precondition guidance, though it never states when NOT to use the tool or which sections are mutually exclusive.

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