graph_metadata

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

With no annotations, the description must convey behavior. It indicates read/validate operations, implying no mutation, but fails to disclose error handling, return shape, or side effects. It does specify 'project-local' scope, but otherwise lacks transparency about validation criteria or failure modes.

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 two short phrases with no fluff. It front-loads the core purpose and action list, making it easily scannable and appropriately concise.

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 lack of an output schema and the presence of a nested metadata object, the description is too terse. It doesn't explain return values of get/validate, how the metadata parameter is used, or what 'validating' entails. A user cannot fully anticipate behavior from the description alone.

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?

The input schema has 100% description coverage, so the schema already documents the three parameters. The description adds no new semantic detail beyond restating the action enum. Therefore the baseline of 3 applies.

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 uses specific verbs 'read' and 'validate' with the resource 'project-local graph metadata sidecar', and clearly enumerates the two actions 'get|validate'. It identifies scope with 'project-local', but doesn't explicitly contrast with sibling tools, so the purpose is clear but not fully differentiated.

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 does not state when to use this tool or provide alternatives. It lists actions but gives no guidance on choosing between get and validate, nor any conditions for when this tool is appropriate relative to other metadata tools. Usage is only implied by the action names.

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