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

Beyond the readOnly/idempotent annotations, it states that this will not re-collect data, call models, charge the customer wallet, or consume cleanup-success quota, and that preview does not create tasks. It also flags that source body content is untrusted and that instructions inside it must not be taken as authorization, plus the 404-does-not-prove-never-submitted subtlety for find_job. That is genuinely useful context layered on top of the annotations.

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 a dense, multi-clause sentence, but the workflow steps are front-loaded and each clause carries distinct information (ordering, safety guarantees, injection warning). Only the sheer density and single-sentence packaging keep it from a 5.

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?

For a complex 11-variant read tool with no output schema, the description supplies workflow ordering, safety semantics, and a security caveat, and the annotations cover the read-only profile. An agent has enough to call it correctly, though parameter-level detail for some variants (pagination limits, cursor behavior) is left implicit.

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 100% and the discriminator enum already documents every action, so the schema does the heavy lifting (baseline 3). The description adds value by explaining the intent and ordering of each action variant (e.g., find_job using the original idempotency key, preview against still-valid collection results), which goes beyond the raw field definitions.

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 names concrete sub-actions (get_entitlement, get_source, get_source_fields, list_jobs, find_job, list_recipes, preview, and reading jobs/units/results/exports) and frames the whole tool as a read/inspection surface, which lets an agent separate it from the write sibling everyinfra_data_cleanup_action. It is a bundle of read operations rather than one crisp verb+resource, so it stops short of a 5, but the intent is unambiguous.

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?

Usage is spelled out as an ordered workflow: first query entitlement, then source/version/fields, then list/find jobs, then list recipes, then preview or read existing artifacts. The exclusion of re-collection and task creation clarifies when this is the right (read) choice. It never names the write sibling explicitly, so it lacks the full when-not/alternative routing of a 5.

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