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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, but the description adds genuinely new behavioral facts: it never contacts the provider and never incurs spend, and the cost field distinguishes settled, in-flight and unknown. What is missing is behavior on failure (unknown job_id, or neither identifier supplied).

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 dense sentences with the free/read-only guarantee front-loaded and the routing hint last; nothing is redundant or repeated from the annotations.

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 well by listing state, steps, results, cost and next action. It stops short of explaining what happens when neither job_id nor request_id is provided, which is a real gap for a 0-required-param tool.

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 only 33% — job_id and request_id have no descriptions — and the description only says "by job_id or request_id", which hints that either key works but never states that at least one is effectively required (required list is empty). It compensates partially, not fully, 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 concrete resource (a research job) and enumerates exactly what is returned: state, steps, results so far, cost breakdown and next action, plus the two lookup keys. It names the sibling (start_research_job) used to advance a job, so it is distinguishable from the surrounding research tools at a glance.

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?

"to go on with a job, call start_research_job with its request_id" gives an explicit alternative plus the condition that selects it. It does not cover the other adjacent case (cancel_research_job) or whether this is meant to be polled repeatedly, so it falls short of full when/when-not coverage.

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