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

With idempotentHint=true already declared, the description goes well beyond it by spelling out the exact idempotency contract: same key plus same payload returns the original job, while a changed payload for that key is a conflict. It also discloses the 16 KiB encoded-size cap, the 100-job lifetime quota that counts completed and failed jobs, and a no-secrets/no-PII constraint - all operational facts the annotations cannot express.

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?

Four short sentences, front-loaded with the action and credential, then the idempotency rule, then limits. Dense and mostly waste-free, though the opening clause overlaps with what the schema already says about write_token and job_key.

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?

An output schema exists, so return values need no explanation, and the description covers the failure modes an agent actually needs: conflict on changed payload, size cap, and lifetime quota. The remaining gap is minor - nothing about what a conflict error surfaces or whether enqueueing is allowed once the 100-job limit is hit.

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 100%, so all four parameters are already documented with patterns and meanings, making 3 the baseline. The description restates the write-token role and the stable job_key concept and adds the encoded-size framing, but contributes little meaning the schema does not already carry.

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 gives a specific verb and resource ('Add a JSON job') plus the required credentials, which is clearly distinct from the claim/ack/read siblings in this queue family. It stops short of naming a sibling tool by name, but the enqueue-vs-process distinction is unmistakable from the verb.

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 by the idempotency and quota rules, which tell an agent this is the write path for creating jobs. However, there is no explicit 'use this before claim_agent_queue_job' framing, no statement that the queue must already exist (that hint lives only in the queue_id schema description), and no when-not guidance.

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