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

Beyond the annotations, the description discloses the cost model (this call charges nothing, returns payment_url/price/instructions), the exact payment protocol (MPP, HTTP 402, Stripe shared token), and the charge condition (only if the run passes its controls). It also describes output behavior — named exclusions with reasons and per-figure 10-K citations — which is exactly the behavioral context annotations cannot convey.

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 output scope is front-loaded, followed by controls, then the payment mechanics, so the agent learns what it gets before how it pays. Sentences are long and dense with parentheticals, but essentially every clause carries information an agent needs to act correctly.

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 paid, asynchronous-style tool with no output schema, the description still covers data source, freshness, peer-count bounds, exclusion reporting, citation guarantees, and return contents (payment_url, price, instructions). Nothing an agent needs in order to call it, or to explain the result to a user, 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 67%, and the description compensates by expanding the metric enum into plain-language definitions (revenue growth, gross margin, R&D and sales-and-marketing as a share of revenue) and restating the 2-6 peer constraint and fiscal-year alignment. The ticker parameter gains no meaning beyond the enum list, which is the only real gap.

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 a specific artifact (a citable peer comparison of one company's filed metric against 2-6 peers, latest fiscal year, from SEC EDGAR XBRL) and clarifies that the call itself is a quote, not the run. It is clearly distinct from read-path siblings like get_decision_evidence, but it does not explicitly contrast with other run_* siblings such as run_filing_trend or run_triangulation.

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 rather than stated: you call it when you want a peer benchmark, and the description explains the follow-on payment step. There is no explicit 'use this instead of X when Y' routing against the many sibling run_* tools, and no preconditions (e.g., which tickers are valid) beyond what the enum encodes.

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