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

Goes well beyond the readOnly/idempotent/destructive annotations by disclosing that it starts no lookups and spends no credits, that results are capped at 200 rows per call and paged via offset, that paused jobs report a reason, and how pending/unpaid rows behave. It even carries interpretive guidance for result values (valid = found and confirmed and safe; catch_all = best guess, unconfirmed, may bounce; not_found/no_mail_domain/retry_later) plus an instruction to tell the user which addresses are unconfirmed.

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 what the tool shows and who it is for, and the alternative is named in the second sentence where an agent will look for it. It is a dense, somewhat run-on block that folds in result-value semantics and a docs link; the content earns its place but could be broken into shorter scannable lines.

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-value structure need not be re-explained, and the description still covers the non-obvious parts: cost behavior, pagination, job state vocabulary, result-value meaning and the resume/cancel boundary. For a read-only polling tool with four fully documented parameters, nothing an agent needs in order to call it correctly 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 coverage is 100%, so the baseline is 3; the description earns above baseline by explaining the practical effect of include_results=true (up to 200 result rows per call, paged with offset) and clarifying that waiting rows surface as pending and credit-held rows as unpaid until resume, which affects how limit/offset are interpreted. It does not restate the job_id pattern or the numeric bounds, but those are already fully documented in the schema.

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 ('Show a list started with argorant_find_emails') and enumerates exactly what is returned: status, done/waiting counts, per-result counts, credits charged, spending limit and pause reason. It distinguishes itself from both sibling endpoints (argorant_find_emails to start, argorant_manage_find_emails to resume/cancel) without the agent needing to open any 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?

Gives an explicit when-to-use ('Use it to follow the list') plus an explicit routing rule for the alternative ('to resume or cancel it use argorant_manage_find_emails'). It also tells the agent when to set include_results=true and when rows are pending versus unpaid, so nothing about selection is left to inference.

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