pocketdraft_validate_project

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is carried for free. The description adds real behavioral content beyond that: the validation rules applied (missing assets, bounds, crop, browser-font text layout), the explicit exception that overlaps are allowed rather than errors, and the dry-run mode for layout.sync. Only the response payload shape and any error/threshold behavior are left unstated.

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?

Three tight sentences, front-loaded with what is checked before the optional mode is mentioned; no filler. The only blemish is the unexplained dotted token 'layout.sync', which is concise but slightly opaque to an agent that has not seen that vocabulary elsewhere.

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?

An output schema exists, so return values needn't be documented, and the mandatory path (projectId only) is adequately covered by the validation-rule sentence. The gap is the optional layoutSync preflight: a deeply nested object with zero parameter documentation and only a one-clause mention in prose, which is thin for a tool whose main differentiator is that mode.

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 0%, so the description shoulders the full burden, yet it only gestures at layout.sync as a named concept without explaining projectId, revision, or any of layoutSync's nested structure (targetCanvasIds, scope, fields, mapping, locale). Given the single optional parameter is a deep nested object, this leaves a calling agent with no semantic guidance for the most complex part of the contract.

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 names a concrete verb (Check) and enumerates the exact resources validated: missing assets, bounds, crop, and text layout with browser fonts. An agent knows precisely what the tool returns information about. However, it never distinguishes itself from the similarly-named sibling pocketdraft_inspect_project, so the boundary between 'validate' and 'inspect' is left to inference.

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 second half of the description does imply a usage mode: optionally preflight a layout.sync without mutating the project, i.e. dry-run semantics. But there is no explicit when-to-use or when-not-to-use guidance, and no sibling alternatives (inspect_project, preview, export) are named. This is implied usage rather than stated guidance.

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