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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false). The description adds genuinely useful behavioral context beyond that: the semantics of saved_schema_deployed across all three states (true/false/null) and the meaning of undeployed_changes. This is valuable return-behavior disclosure that neither the schema nor annotations provide.

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 sentences, well front-loaded: the core action first, then the format distinction, then the deploy-status semantics. The second sentence partially restates the first (nodes/entities/relationships appear in both), so it is not maximally lean, but each sentence still carries meaningful information.

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 single-parameter, read-only getter with full schema coverage and safety annotations, the description is nearly complete: it explains what is returned, how graph schemas differ from relational flat-table schemas, and the semantics of the deploy-status field. The only gap is not pointing to version-history or template siblings, which is a nice-to-have rather than a correctness issue.

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% — project_id is already documented as a UUID string. The description adds no parameter-level detail beyond 'of a project,' which merely echoes the schema. With full schema coverage, baseline 3 is appropriate.

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?

Opens with a specific verb+resource: 'Get the graph schema definition of a project.' The description then specifies the return shape (hierarchical schema with nodes/relationships) and explicitly contrasts it with relational flat-table schemas, distinguishing it from siblings like get_schema. The tool's purpose is unambiguous and 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?

Provides clear context that this retrieves the hierarchical graph-schema format rather than a relational flat-table schema, which helps an agent choose between get_graph_schema and get_schema. However, it never names sibling alternatives such as get_graph_schema_at_version or get_graph_template_schemas, and gives no explicit when-not guidance for those cases.

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