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

No annotations are present, so the description carries the full burden. It discloses two meaningful behaviors: no live-web access and the need for a funded API key. However, it omits other behavioral details like result ordering, pagination, or read-only implications. Adequate but not rich.

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 short sentences with no filler. The most important scoping fact ('does not visit the live web') is front-loaded, and the API key requirement is included as a necessary caveat. Every sentence contributes.

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 search tool with no output schema, it covers the essential context: the stored corpus, the live-web exclusion, the natural follow-up tool, and the authentication requirement. The only notable omission is the meaning of the limit parameter, though its default and bounds in the schema make it inferable.

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 schema already describes q and max_age_s, but limit has no schema description. The tool description adds no parameter-specific information beyond what the schema provides, so it neither compensates for the missing limit description nor increases clarity. With 67% schema coverage, a baseline of 3 is appropriate.

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 states a specific action ('search') and a precise resource ('pages already stored in AfterImage'), and adds a distinguishing constraint: 'Does not visit the live web.' It also mentions the sibling get_page, making the tool's role clear.

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?

It explicitly clarifies this tool searches an offline corpus only, ruling out live-web queries, and provides a follow-up instruction: 'Then call get_page for the full text of a hit.' This is actionable, though it does not explicitly describe when get_page would be used alone or other alternative conditions.

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