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

Annotations already declare readOnlyHint=false, openWorldHint=false, and idempotentHint=true, so the bar is lower, yet the description adds real context: the hidden shopper-session dependency, the intake_access_token bearer fallback for hosts that cannot preserve session state, and delivery timing (~5-10 minutes for secure checkout). It does not quantify size limits or describe error behavior, keeping it short of a 5.

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?

Purpose is front-loaded, but the paragraph then sprawls through session-preservation rationale, retry guidance, batch preference, and checkout timing in one run-on block. Several clauses (the Coverage Cat narrative, checkout timing) could be trimmed or condensed without losing actionable content.

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 return values need not be explained, and annotations cover the safety/idempotency profile. The description supplies the flow phase, prerequisites, mode choice, and auth fallback needed to call it correctly, leaving only minor gaps like payload size limits.

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 57%, so some compensation is warranted. The description explains that uid alone may suffice when the session is preserved, that attachments is the preferred single-turn batch mode, and how intake_access_token is reused across retries. These add usage meaning beyond the schema's per-field text, though the base64 mechanics are restated from the schema rather than extended.

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 ('Upload declarations or auto declarations') and pins it to a precise flow stage ('consumer-prefill umbrella post-choose flow'). It is readily distinguishable from siblings like umbrella_consumer_prefill, umbrella_consumer_select, and umbrella_consumer_bind without opening any 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 explicit preconditions ('Use only after selection and only when Coverage Cat says documents are needed') and names concrete alternatives: prefer a single batch attach call when both files exist, and use the REST binary fallback when raw bytes/disk files are available. It also rules out dropping to raw HTTP or asking the shopper for credentials. This is near-complete routing guidance.

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