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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: no charge or mutation occurs, charge due today vs later charges, wallet/auto-reload coverage, upper-bound billing semantics, and the paused-campaign case where charge due today is 0 and charged_on_resume is true. That is exactly the behavioral detail an agent needs before quoting a price.

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?

Front-loaded with the core purpose and cost breakdown, followed by the upper-bound and paused-campaign rules. The closing sentence 'Retrieves data without changing records or spending credits' restates what the second sentence already said and what readOnlyHint/destructiveHint annotations cover, so there is minor redundancy.

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?

Covers the full decision surface for a read-only estimate: what is returned conceptually (charge today, later charges, wallet coverage flag), no side effects, billing edge cases (skipped properties, paused campaigns). With no output schema needed for an estimate preview and annotations carrying the safety profile, nothing essential 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?

With schema description coverage reported at 0%, the description must carry the load. It clarifies what count means (properties planned to add, upper bound, skipped ones not charged), which is valuable, but it never explains the path.id parameter beyond the schema's generic 'Resource ID' (i.e., that it is the campaign id). Partial compensation only.

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+resource: estimating the cost of adding a number of properties to a mail campaign. The line 'Nothing is added or charged' implicitly distinguishes it from dealmachine_mail_campaign_add_properties, and the count framing separates it from the campaign cost_estimate sibling. An agent can tell what this does without opening the schema.

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?

Clear usage context: run this to preview the charge before adding properties, with the caveat that the count is an upper bound because skipped properties aren't charged. It explains paused-campaign behavior as a usage scenario. It stops short of explicitly naming dealmachine_mail_campaign_add_properties as the follow-up action, so no named alternative.

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