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

Annotations only declare it is a safe read; the description adds substantive traits: a 64 MB payload cap, base64-encoded file bytes, an MP4 link that is private and short-lived, and the fact that access is re-verified at download time. These are non-obvious constraints an agent could not get from structured fields.

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?

Three tight sentences, front-loaded with what is retrievable and the format mapping, followed by the payload-encoding rule and the integrity guardrail. No sentence is 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?

Covers format semantics, size limits, encoding, link lifetime, and reference integrity — enough to invoke correctly and handle the response, and the output schema carries the return shape. Minor gap: it doesn't clarify whether format is optional or whether certain formats are only valid for certain output types.

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 low (25%), so the description must carry weight, and it does for `format` by mapping each enum value (md, pptx, pdf, mp4) to a concrete artifact type and delivery mode. It says nothing about the required session_id/output_id pair or the organization_id billing scope, leaving part of the parameter set to the schema.

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 and resource ('Retrieve a saved report') and enumerates the concrete artifact types (Markdown, PPTX/PDF, MP4 highlights). It doesn't name which sibling is the alternative (e.g. get_research_deliverable vs download_research_output), so the boundary is inferred rather than stated.

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 operating guidance for the result: decode base64 into an artifact instead of showing it to the user, and never fabricate download URLs. It does not say when to pick this tool over get_research_deliverable or when a given format is unavailable, so exclusions are missing.

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