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

Annotations already indicate destructive and idempotent behavior, but the description adds valuable disclosure: it states that source contents, secrets, commands, diffs, logs, environment values, and credentials are rejected (privacy filtering), that Brain Scanner computes canonical sizes and digests internally, and that the changeNarrative must be manually authored. This goes beyond the annotations and clarifies important behavioral boundaries, though it does not detail what happens on failure or conflict.

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 sentences, front-loaded with the core purpose and key constraints (atomic, bounded, privacy-filtered). The second sentence adds a critical operational requirement (manual changeNarrative) without redundancy. Every word earns its place; it is appropriately sized for the complexity.

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 parameters, nested objects, atomicity, no output schema), the description is incomplete. It does not explain the expected behavior of idempotencyKey or expectedProjectVersion, the structure/limits of nodes and edges, or what the return value or side effects look like. While it mentions atomicity, it omits conflict handling, version validation, and the overall workflow. The description leaves significant gaps for an agent to safely invoke this tool.

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 by explaining parameter meanings. It mentions changeNarrative sections and that Brain Scanner handles digests, which hints at mappedRevision or similar, but it does not explain projectId, expectedProjectVersion, idempotencyKey, nodes, edges, or sessionId. The description adds only minimal meaning beyond the schema, leaving most parameters semantically opaque for an agent.

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 action: atomically publishing a bounded, privacy-filtered project graph. It identifies the specific resource ('project graph') and adds unique qualifiers ('bounded, privacy-filtered') that distinguish it from generic publish operations. It does not explicitly name sibling tools like patch_project_graph or validate_project_graph, but the phrase 'Preferred agent path' implies alternatives exist, earning a 4 rather than a 5.

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 says 'Preferred agent path,' which signals this is the recommended tool for publishing a project graph, but it does not specify conditions for when to use it over alternatives (e.g., patch_project_graph) or when not to use it. It does clarify a critical prerequisite: the publishing agent must manually write the changeNarrative sections. This gives context but lacks explicit exclusions or alternative routing.

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