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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing the default-off treatment of discontinued cards and the exact field set returned per card (slug, fee, base earn, grade, check date, source, page URL). It says nothing about result ordering or what an empty result means, but with annotations carrying the safety load a 3 is fair.

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?

Three tight sentences, front-loaded with purpose, then the return fields, then the exclusion default and workflow hint. Nothing is padding — even the field enumeration earns its place because there is no output schema.

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?

With no output schema, the description correctly compensates by listing the returned fields, and it covers the default limit omission, the discontinued-cards default, and downstream slug usage. The only unaddressed item is ordering/pagination of results and result-set size behavior, which is minor for a capped-limit search tool.

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 every parameter including fee_band bands and the issuer slug caveat is already documented in the schema. The description's main addition is framing the three booleans as a coherent filter group and noting the default exclusion of discontinued cards; otherwise it largely restates what the schema provides. Baseline 3 applies when the schema does the heavy lifting.

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?

Opens with a concrete verb and resource ("Finds Indian credit cards") and enumerates the searchable facets: name, issuer, network, fee band, plus three named filters. It also distinguishes itself from the sibling get_card by stating that slugs produced here feed "every other call," so an agent knows this is the discovery entry point rather than a detail lookup.

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 clear operating context: use it to find cards by facet, and reuse the returned slug in other calls. It also states the default exclusion rule (discontinued cards omitted unless include_discontinued is true). It stops short of naming when to prefer the recommend sibling over manual filtering, so routing is implied rather than explicit.

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