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

Annotations indicate destructiveHint=true and idempotentHint=true, and the description aligns with these by stating it 'replaces' a graph and 'never creates' anything. The description adds valuable context that it only affects exactly the existing project, which is not visible in annotations. It discloses the destructive nature and the requirement for manual narrative, though it doesn't elaborate on failure behavior or auth requirements, which are minor for this 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 a single, dense paragraph with no fluff. It front-loads the core action ('Replace') and the explicit exclusions, making it scannable. However, it is somewhat long for an MCP description, though every sentence earns its place by preventing misuse.

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 (8 params, nested objects, no output schema), the description covers the critical behavioral aspects: scope, exclusions, and the manual narrative requirement. It does not describe the return value or error conditions, but since there's no output schema, that gap is notable. Still, it's sufficient for an agent to call correctly if it understands the domain.

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 must compensate, but it only mentions projectId and changeNarrative, leaving nodes, edges, expectedProjectVersion, idempotencyKey, and others unexplained. However, the schema itself is fairly descriptive (e.g., field names like nodes, edges, changeNarrative are self-explanatory), so the agent can infer meaning from schema structure. The description adds value for changeNarrative but not for the complex nested objects.

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 purpose: replacing the privacy-filtered published graph for an existing Brain Scanner project, identified by projectId. It uses specific verbs ('replace', 'never creates') and distinguishes from siblings like publish_project_graph and patch_project_graph by emphasizing it does not create, infer, inspect, or change Git/GitHub. The scope is precise and unambiguous.

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 explicitly states what the tool never does (creates project, infers by display name, inspects repository remotely, changes Git or GitHub), which helps the agent avoid misusing it. It also instructs the publishing agent to manually write the four changeNarrative sections, leaving no doubt about the required workflow. This is a strong when-to-use vs when-not-to-use guidance.

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