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

Goes well beyond the annotations by disclosing single-use semantics, expiry, that 'bytes are never returned inline,' that exact idempotency_key replay returns identical sessions, and that 'reminting never mutates the artifact' - resolving the apparent tension between 'Creates' and readOnlyHint=true. It also states the tool is 'Not metered,' which no annotation conveys.

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 action and result, then a second paragraph of operational cautions. Dense but every sentence carries information; the nested parenthetical defining chart_id/declaration_id is the only slightly heavy passage.

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?

An output schema exists, so the description needn't document the returned programs or hashes. Given that, it covers purpose, lifecycle (single-use, expiring), idempotent replay, integrity verification, and non-mutation - the main gaps are the undocumented workspace_tag and expires_in_seconds semantics.

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 description has to compensate. It explains the items subjects well ('a retained handle, an admitted source_document_id, or an admitted chart_id or declaration_id') and the idempotency_key replay contract, but workspace_tag, client_item_id, and expires_in_seconds (default 3600, max 86400) are never mentioned anywhere.

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 and resource: 'Creates single-use, expiring download programs for one or more authorized immutable artifacts,' with a signed GET program per item. It doesn't explicitly name the sibling it differs from (create_view_link / create_upload_sessions), so an agent must infer the download-vs-upload-vs-view distinction from 'signed GET program' alone.

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 guidance: 'Verify every download against the returned SHA-256' and 'A failed or consumed GET needs a new session - mint again rather than retrying the signed URL.' It also warns not to retry signed URLs, which prevents a common failure mode. It stops short of naming alternative tools for cases where a persistent or non-force-download link is needed.

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