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

With no annotations provided, the description carries the full burden and does well: it discloses that the tool is deterministic, uses no LLM, is fast ('seconds per call'), is informational only ('a record of what happened, not a prediction'), and has a specific not_found behavior with nearest candidates. It also discloses pricing and payment method. It does not mention rate limits or whether the underlying API could fail, but for a read-only informational tool the disclosed traits are substantial.

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 a single dense paragraph that front-loads the core question and then lists outputs and behaviors. Every sentence adds information: input forms, output fields, data source, determinism, fallback behavior, informational nature, and pricing. It is slightly long but each clause earns its place; the pricing sentence could arguably be trimmed, but it is relevant for an agent deciding whether to call a paid tool.

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 single-parameter read-only tool with no output schema, the description is nearly complete: it covers inputs, outputs, source, failure mode, and cost. The only gaps are minor—no explicit mention of rate limits, no example slug/condition id format, and no statement about what happens on API errors. Given the tool's simplicity and the absence of annotations, this is a strong, complete description.

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% and the single parameter 'market' is already described in the schema as accepting a slug, condition id, or free text. The description adds meaningful semantics by explaining how the free-text form is handled (not_found with nearest candidates) and by listing the output fields that the parameter will produce. This goes beyond the schema's bare type/format description, though it doesn't add syntax details like slug format examples.

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 question ('Has a Polymarket market resolved, and how?') and names the exact resource (Polymarket market resolution status) and the verb (check). It enumerates the concrete outputs (status, winning outcome, payout vector, close time, mechanism, days after end, last traded price, best bid/ask, categories) and the input forms (slug, condition id, free text), which fully distinguishes it from the sibling tools like claim_check or token_check.

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?

The description clearly states what inputs to provide and what the tool returns, and it explicitly notes the free-text fallback behavior ('a free-text question that matches no market is answered as not_found with the nearest candidates'). It does not explicitly name sibling alternatives or say when not to use this tool, but the context signals show siblings are unrelated (claim_check, token_check, defi_protocol, etc.), so the usage context is clear enough without exclusions.

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