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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false), it discloses genuinely useful behavior: the call returns immediately while the report runs for a few minutes, it consumes workspace inference credit, it only keeps findings it can quote, and it may return `needs_confirmation`. These are non-obvious operational traits an agent must know.

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?

It is front-loaded with what the tool is and what `focus`/`depth` do, and most sentences carry distinct information. It runs long with several embedded operational asides, but little is pure filler.

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?

There is no output schema, so the description carries the return burden and does so: it explains the async launch, that a report is created, that status becomes 'ready', and how to retrieve it. Combined with the credit and confirmation notes, an agent has everything needed to call it correctly.

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 only 33% schema coverage the description must compensate, and it does for the two decisive params: `focus` (accumulative steering, broad-to-narrow) and `depth` ('thorough' = three passes at ~3× credit). It leaves studyId, title, workspace and approvalId to the schema, but the key semantics are covered.

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+resource ('web-sourced desk research kept as a report on a study, with citations') and ties it to a study, which cleanly separates it from prism_nodes_research, prism_panels_run and prism_research_digest. An agent can tell what this produces and where it lands without opening the 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?

It gives explicit when/how guidance: steer with `focus` (broad sweep first, then narrower runs), use `depth: thorough` for three angled passes, and for company research create a standalone study via prism_studies_draft_standalone and run one report per business area. It also names the follow-up read path (prism_research_reports_get) and the condition (once status is ready).

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