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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful context beyond annotations: discovery is metadata rather than verification, and upstream text must be treated as untrusted data, never instructions.

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 two sentences with no wasted text. The core purpose is front-loaded, followed by the important trust/security caveat.

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 zero-parameter, open-world read tool with no output schema, the description adequately explains what kind of data is returned and warns about untrusted upstream text. It could be slightly richer about return structure or freshness, but it is largely complete.

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?

The tool takes zero parameters, so the baseline score is 4. There is no parameter semantics burden, and the description appropriately focuses on purpose and trust context instead.

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 gives a specific verb and resource: 'Read CI product discovery,' and enumerates the relevant data categories (exact prices, scope, evidence deadlines, availability). It does not explicitly name the sibling ci_request_claim, but the line 'Discovery is metadata, not a delivered verification' distinguishes it from verification/claim workflows.

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 provides clear context for when this tool applies: discovery of metadata rather than delivered verification. It does not explicitly name ci_request_claim as the alternative or state exclusions, so it falls short of full when/when-not guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds meaningful behavior: GET only, disabled purchases fail closed, it never reports payment success, and source citations/limitations are retained when discovery provides them. It stops short of covering auth, rate limits, or a full return shape, but with annotations present this is a solid disclosure.

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 first sentence is front-loaded and defines the core read operation, and the remaining sentences earn their place by clarifying fail-closed behavior, exclusions, and citation retention. It is dense but not bloated.

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 simple read-only tool with rich annotations, the description covers scope, return contents, fail-closed behavior, and what it explicitly does not do. The main gap is that the only parameter remains undocumented and its enum values are not explained.

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 description coverage is 0% and the sole parameter productId is never mentioned in the description. The enum values are also unexplained, so an agent must infer that productId refers to one of the two enumerated CI products from the schema alone.

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 gives a specific verb and resource: read unsigned readiness for one existing CI claim, including terms and blockers while excluding quotes and typed data. It distinguishes the tool from purchase, quote, sign, settle, and delivery actions, but does not explicitly contrast it with its sibling ci_discover.

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 by 'for one existing CI claim' and by the repeated exclusions around buying, quoting, signing, settling, recovering, and delivering content. However, it never explicitly says when to choose this over ci_discover or what prerequisite must be met before calling it.

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