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

The description discloses critical behavior beyond annotations: 'This only saves the schema. You MUST call deploy_graph_staging afterwards to deploy.' It also warns about following schema rules, implying validation. This adds context on side effects and prerequisites. No contradiction with annotations exists.

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 well-structured with a clear summary line, a rule list, and a numbered workflow. The key constraint ('saves to database, does NOT deploy') is front-loaded. While lengthy, every section serves a purpose—the rules are necessary for schema correctness and the workflow for proper deployment sequence.

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 complexity (nested schema object, required workflow), the description covers the crucial context: what it does, what it doesn't do, how to use it in the deployment pipeline, and schema requirements. It lacks explicit return-value information, but given the absence of an output schema and the strong workflow context, the description is sufficiently complete.

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 already describes both parameters (project_id as UUID string, schema as object with nodes/relationships). The description greatly enriches the schema parameter by detailing required structure: nodes key with entities, field definitions, types, cardinality, and naming conventions (PascalCase, UPPER_SNAKE_CASE). This goes far beyond the schema description and is essential for correct invocation.

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: 'Update a graph project's schema (saves to database, does NOT deploy).' It uses a specific verb ('update') and resource ('graph project's schema'), and distinguishes from deployment tools by explicitly noting it does not deploy. This separates it from siblings like deploy_graph_staging and update_schema.

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 an explicit workflow: use get_graph_schema first, then update_graph_schema, then deploy_graph_staging, and monitor with get_job_status. It also says 'You MUST call deploy_graph_staging afterwards to deploy,' making the usage context unmistakable. It further references rules from create_graph_project, which serves as a guideline for schema structure.

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