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

The description discloses several behavioral traits beyond the annotations: it warns that omitting project_id 'creates a NEW, unrelated project and strands the old one,' notes that input is validated against @clipkit/protocol, and explains that 'the runtime ignores unrecognized keys, and this tool flags any it does not recognize.' These details align with the destructiveHint annotation and add valuable operational context.

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 appropriately sized for the tool's complexity. It is front-loaded with the core purpose, followed by usage rules, revision guidance, and validation/shape details. Every sentence earns its place—there is no filler or redundancy, and the logical flow makes it easy to parse.

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?

Given the tool's high complexity (nested source object, side effects, validation), the description covers all necessary context: return value (project_id), when to use alternatives, revision behavior, validation details, and pointer to get_schema for exact field definitions. The presence of an output schema does not reduce the need for this explanation, as the description adds decision-making context beyond any structured fields.

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?

Although the schema covers 100% of parameters with descriptions, the tool description adds significant meaning: it elaborates on project_id's usage ('ALWAYS pass it once a project exists in this conversation'), explains the consequences of omission, and describes the source object's shape, noting optional fields and directing to get_schema for exact field names. This goes well beyond the schema's terse 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 clearly states the tool's function: 'Replace the entire project with the given source JSON, returning its project_id.' It uses a specific verb ('replace') and resource ('project'), and explicitly differentiates from siblings by naming edit_element, add_element, and delete_element as alternatives for single-element changes.

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 provides explicit when-to-use guidance: 'This is the PRIMARY way to build: use it to create a composition or to add/change many elements at once.' It also gives a clear exclusion rule: 'To tweak a single element in an existing project, use edit_element / add_element / delete_element instead.' The 'REVISION RULE' paragraph further details when to pass project_id versus when to omit it, offering unambiguous decision guidance.

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