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

With no annotations, the description carries the burden and does a good job: it discloses the return shape (best position plus every non-overlapping position above threshold, as pixel boxes with scores), the engine used, and the per-call price of $0.003. It does not cover auth requirements or rate limits, which is the main remaining gap.

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 sentences, each earning its place: purpose first, return shape second, routing rule and price last. No padding or restatement of the name.

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?

There is no output schema, so the description must cover returns, and it does (best position, all non-overlapping matches, pixel boxes with scores). Combined with 100% schema coverage of inputs, an agent has everything needed to call this correctly.

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 100%, so every parameter is already documented in the schema, including method enum trade-offs and score normalization. The description adds only marginal context ('scoring above the threshold') and no syntax beyond what the schema supplies, so the baseline 3 applies.

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?

Names a specific verb and resource ('Find where a small pattern image ... appears inside a larger screenshot') and identifies the underlying algorithm (cv2.matchTemplate). It explicitly distinguishes itself from the sibling homography tool by scoping to 'exact-looking pixel patterns at the same scale'.

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 both a when-to-use condition ('exact-looking pixel patterns at the same scale') and a when-not with a named alternative ('for different scale, rotation or perspective use /v1/homography'). The agent can route between template-match and homography without opening either schema.

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