get_batch_status

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description goes further by listing the returned artifacts and, crucially, decoding a status value ('ready_for_visual_review means structural checks passed, not visual approval') and forbidding auto-restart of failed jobs. That is real context beyond structured fields, though it says nothing about polling cadence or job retention.

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 compact sentences, front-loaded with the read action and return contents, then the status-semantics caveat and the restart warning. Every sentence carries content, though the first sentence is a dense packed list rather than a clean statement of intent.

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 carries the return-value burden and does it reasonably: progress, plan, log and preview paths plus the meaning of the key status flag. What remains thin is the input side (how to obtain a valid job_id) and any note on long-running or partial jobs.

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?

One parameter with 0% schema description coverage, so the burden falls on the description, which only indirectly covers job_id via 'Read a background card job' — it never says the id is the UUID returned by batch_cards or what happens on an unknown/expired id. Marginal compensation for the coverage gap.

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 (Read) and resource (a background card job) and enumerates what it surfaces: per-card progress, prepared plan, log and preview paths. Against siblings like batch_cards, validate_cards and get_runtime_status, an agent can tell what this returns 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?

Usage is implied — poll this after starting a card job — but no alternative is named and no when-not condition is given, aside from a behavioral prohibition ('Never automatically restart failed or unconfirmed jobs'). That prohibition is guidance about how to act on the result, not about choosing this tool over a sibling.

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