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

Goes well beyond the annotations by disclosing the incremental read scope, that prior themes are preserved, that the call returns immediately while work continues server-side, that it consumes inference credit, and that it may return needs_confirmation. These are exactly the behavioral traits an agent needs and none are derivable from readOnlyHint/destructiveHint alone.

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?

Front-loaded with the core action, then layers the async/cost/edge-case details in a single dense paragraph where each sentence carries information. It is a touch dense but nothing is redundant.

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 does the right thing by describing the return shape (phase, upToDate, needs_confirmation) and the polling workflow. It is nearly complete for a mutation tool, but omits how to act on a needs_confirmation result and how approvalId relates to it.

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 coverage is only 50% (studyId and approvalId undocumented), so the description must carry more weight. It implicitly contrasts incremental mode with a full re-read, which maps onto reanalyzeAll, but it never names that parameter and says nothing about approvalId even though it warns about needs_confirmation. Adequate but leaves real gaps.

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+resource ('kicks the theme analysis') and immediately scopes it as incremental with the prior themes carrying forward, which an agent can distinguish from a read tool like prism_studies_get. It also names prism_studies_get as the follow-up reader, so the purpose is unambiguous without opening either 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?

Gives clear operational context: run when you want fresh theme analysis, expect an async run, wait and re-read prism_studies_get, and treat upToDate:true as a healthy no-op rather than an error. It stops short of an explicit when-not-to-use or a comparison against the full clean-slate (reanalyzeAll) path, so it is strong context rather than full routing guidance.

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