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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond that by disclosing the status state machine, the meaning of overlimit for the account, polling semantics for pending/processing, and the full return payload shape. It also flags a conditional behavior not visible in annotations: project_id is inferred for single-project customers but required otherwise.

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 purpose and intent, then usage, then the return shape and parameter sourcing — a sensible information hierarchy. The long comma-separated enumeration of return fields is dense but justified because no output schema exists; it could be trimmed or formatted for easier scanning.

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?

With no output schema, the description supplies the return fields and the status enum itself, and it explains what each status implies for the caller. Combined with the sibling disambiguation and parameter sourcing, nothing essential for a correct invocation is missing.

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 must carry the load, and it does: feed_id is sourced from list_feeds/create_feed and project_id is marked OPTIONAL with the inference rule and the fallback when project_id_required occurs. Minor gap: no format/validation detail beyond the sourcing hint, though the schema's integer/exclusiveMinimum constraint covers type.

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?

Opens with a specific verb and resource ("Get the runtime status of one feed") and immediately enumerates scope: generation state, progress, last run/submit, error. It explicitly contrasts itself with the closest sibling, get_feed, for configuration/mapping, so an agent can distinguish them without opening a 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?

States the triggering intent ("check whether a feed export or submission has finished"), the alternative (get_feed) and when to prefer each, plus concrete next actions per status value (generated → verify_feed_attributes then submit_feed; error → fix and export_feed; overlimit → explained). It also covers the project_id_required recovery path via list_projects.

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