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

The annotations already provide idempotentHint=true and destructiveHint=false. The description adds valuable behavioral context beyond that: the server recomputes implementation and release-evidence meters, and it rejects client-supplied scores, source contents, absolute paths, credentials, and private repository data. This informs the agent about server-side behavior and input restrictions, which is genuinely useful and not redundant with the annotations.

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-loads the core action, and avoids fluff. It packs meaningful constraints into a compact space. It loses one point for using dense jargon like 'expectedAssessmentRevisionToken from assessmentProvenance' without elaboration, which slightly hampers immediate readability, but overall it is well-structured.

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 high complexity (7 parameters, deeply nested assessmentProjection, no output schema, and only sparse annotations), the description is incomplete. It does not explain what a 'roadmap assessment' contains, how the server uses the assessmentProjection fields, what the return/response looks like, or how idempotency works in practice. An agent would struggle to construct a valid request based solely on this description and schema.

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?

With schema description coverage at 0%, the description must compensate, but it only implicitly references expectedAssessmentRevisionToken and rejects certain content within assessmentProjection. It does not explain projectId, sessionId, graphDigest, idempotencyKey, or expectedProjectVersion meaning, nor does it clarify how to construct the nested assessmentProjection object beyond what the schema already states. This is insufficient for a 7-parameter tool with a complex nested payload.

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 states a specific verb ('Publish'), a precise resource ('bounded privacy-filtered roadmap assessment'), and a strict condition ('for one exact Brain Scanner graph version'). It clearly differentiates from sibling tools like publish_project_graph and publish_presentation_request by scoping to an assessment and emphasizing privacy filtering and exact version binding.

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 clear context for when to invoke the tool: publishing a roadmap assessment tied to a specific graph version. It also mentions a prerequisite (expectedAssessmentRevisionToken for methodology upgrades), which helps the agent decide if this tool is appropriate. However, it does not explicitly name alternatives or state when not to use it, so it stops short of full exclusion guidance.

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