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

The readOnlyHint and idempotentHint annotations cover the non-mutating, repeatable nature, but the description adds critical context the annotations do not: no storage, no charge, error reporting granularity (every problem at once by field), batch atomicity ('one bad listing refuses the whole batch for free'), and an explicit security warning treating listing text as third-party data rather than instructions. It stops short of explaining output format or exact error payload shape, so 4 is warranted.

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?

The description is front-loaded with the core purpose and then layers conditionals efficiently. It is dense but none of the sentences are idle — each addresses a distinct concern (same args as create_post, payer check, batch mode, security warning). Slightly long, but every clause earns its keep.

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?

For a 15-parameter validation tool with nested objects and no output schema, the description covers what an agent needs: the no-store/no-charge guarantees, required fields for a single listing, the batch alternative with limits and pricing, the optional payer for pre-sign checks, and a prompt-injection warning. Nothing essential for correct invocation is missing.

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%, so the schema already defines all 15 parameters in detail (e.g., body length limits, payer wallet format, location structure, attributes, batch pricing). The description reinforces key semantics — payer is optional and adds payment-cap/duplicate checks, listings must be sent alone — which adds usable signal beyond the schema. That extra routing and optional-payer context lifts it above the baseline 3.

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 opens with a specific verb and resource — 'Dry run of a listing' — and distinguishes itself from the write sibling by stating 'Nothing is stored and nothing is charged.' It also contrasts directly with create_post ('Send exactly the arguments you will send to create_post'), making its role unmistakable among the sibling tools.

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?

It gives explicit when-to-use guidance: before signing, to learn if the daily cap or a duplicate would refuse the request, and exactly how to invoke it — send the same arguments as create_post, add 'payer' for payment pre-checks, or send 'listings' for a batch. The alternative write tool is named, and the batch condition (1-15, one payment, all-or-none) is stated.

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