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

Beyond the readOnly/non-destructive annotations, the description adds genuinely useful behavioral facts: the sort order, that attempt_id is nullable, that prepared_content is deliberately excluded from queue summaries, that the call is free, and that the 'act' scope is required. These are exactly the details an agent cannot infer from the schema or 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?

Three short sentences, each carrying distinct information — scope/ordering, row shape, exclusion and cost. Nothing is redundant and the most important fact (what the queue is) is front-loaded.

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 parameters and no output schema, the description must carry the return shape, and it does (job_id, attempt_id, no prepared_content). It stops short of mentioning pagination or typical queue size, a minor gap for a list 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?

The tool takes zero parameters, which establishes the baseline of 4. The description correctly adds no parameter guidance because there is nothing to describe, though it does describe the shape of returned rows, which is adjacent value.

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 the resource precisely ('Unclaimed preparation jobs'), adds ordering ('oldest first'), and specifies row contents (job_id, nullable attempt_id). It implicitly distinguishes itself from claim-oriented siblings like pick_up_job, but never names a sibling explicitly, so it falls just short of the top tier.

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?

'Free; requires the act scope' gives cost and auth preconditions, which is more than nothing, but there is no statement of when to use this versus pick_up_job or get_loop_status. Usage is implied rather than directed.

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