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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the description doesn't need to repeat the safety profile. It does add genuinely new context: the read is scoped to 'one authenticated user's' data, and it explicitly discloses negative space — raw local research files are intentionally absent — which prevents the agent from expecting file contents.

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?

One dense sentence, front-loaded with the verb and scope, with no filler. It is somewhat list-heavy, but every enumerated item conveys what the caller will receive.

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?

With no output schema, the description carries the burden of describing return content, which it does thoroughly. However, it lacks any routing guidance or prerequisite (how to get a valid projectId), which an agent needs to invoke it correctly in a 22-tool suite.

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 single projectId parameter is documented only by a UUID regex pattern. The description never describes what projectId refers to or where to obtain it (presumably from researchpilot_list_projects), but the parameter is a single self-evident identifier, so the practical gap is modest.

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?

States a specific verb ('Read') and resource (cloud ResearchPilot project state) and enumerates the contents returned: research question, decisions, summaries, stale state, source digests, artifact availability. It is clearly a read-context tool rather than a list or search tool, though it never names the siblings it differs from (e.g. researchpilot_list_projects, researchpilot_get_profile).

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?

There is no statement of when to use this tool, when not to, or which sibling to reach for instead (for example list_projects to find a projectId first, or get_user_memory for cross-project memory). An agent must infer usage entirely from the name and content list.

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