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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds real behavioral context beyond that: the async lifecycle (queued/training/ready/failed) and the instruction to poll, which tells the agent this is a non-terminal-state resource that may need repeated calls.

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?

Two tight sentences: identity and return contents first, usage instruction second. No filler, no restatement of the title, and the poll instruction is placed where it will be read.

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 usefully enumerates what comes back (status, labels, expected accuracy) and explains the polling workflow needed to use it. It could still mention behavior on an unknown or invalid classifier_id, but for a one-param read tool this is close to complete.

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 there is a single required parameter, so the schema already carries the semantics. The description says it fetches 'one classifier' but adds no format or ID-convention detail beyond the schema's own 'dc_...' example. Baseline 3 applies.

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 ('Tuatara Decide: one classifier's status') and enumerates the status domain. The word 'one' implicitly separates it from list_decide_classifiers and decide_predict, but it never names those siblings explicitly, so differentiation is by inference rather than by statement.

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?

'Poll this after creating one' gives a clear use condition tied to the create sibling flow. It does not state when not to use it (e.g. use list_decide_classifiers for all classifiers, or decide_predict once status is ready), so it stops short of full routing guidance.

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