Project settings

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

Annotations already provide readOnlyHint=false and destructiveHint=true, so the agent knows this is a mutating tool. The description adds meaningful behavioral context by stating that city and people persist with the project and that changes can be tested against the score they move. This goes beyond the annotations without contradicting them.

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 one long but well-organized sentence that front-loads primary actions and then devotes a clause to the most important behavioral nuance: the persistence and scoring impact. Every clause earns its place, and there is no filler or repetition of schema content.

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 9-parameter settings tool with nested objects and an output schema, the description covers all major operations and the key cross-tool effect on scoring. It omits details like compass_d, compass_at, and compass_visible, but those are fully documented in the schema, and the output schema covers return behavior. Overall it is sufficient for an agent to select and invoke the tool 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 description coverage is 100% and each parameter already has a detailed description, so the baseline is 3. The description's parameter mentions—properties key/value/null, level, north, city, and people fields—merely summarize what the schema already states. It adds no new semantic information beyond the structured field descriptions.

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 concrete enumeration of actions: 'Rename the project, set or remove project properties ..., set the compass (north), set the city ..., and say who lives there.' This makes the tool's purpose unmistakable and distinguishes it from read-side siblings like get_home and view-oriented tools. The breadth is inherent to a settings tool, but the explicit verb list removes ambiguity.

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 gives clear usage context: city and people 'belong to the project,' so ergonomics, check_layout, and every dry run use the same rules, meaning this is the persistent project-level configuration path. It does not explicitly name alternatives or state when not to use it, so it falls just short of perfect routing guidance.

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