VisionFlow Match

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

With no annotations, the description carries the full burden and does well: it discloses the algorithm, the return shape (good matches as point pairs sorted by distance), scaling/rotation tolerance, and pricing ($0.004 per call). It omits auth/permission requirements and rate limits, so it is strong but not exhaustive.

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 front-loaded with the core action and mechanism, then the usage note and pricing, with no filler sentences. It is dense with technical terms but each clause conveys useful information for invocation.

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 six-parameter tool with no annotations and no output schema, the description covers the operation, algorithm choice, result format, scaling/rotation behavior, sibling alternative, and cost. Only peripheral details (auth, rate limits) are absent, so 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?

Schema description coverage is 100%, so the schema already documents all six parameters, including the ratio, detector enum, max_matches, and max_features semantics. The description largely restates this (Lowe's ratio test, ORB vs SIFT) rather than adding new parameter meaning, so the baseline of 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?

The description states a specific verb+resource (match local features between a pattern and a larger image) and details the mechanism (ORB/SIFT keypoints, BFMatcher.knnMatch, Lowe's ratio test) and output (point pairs sorted by distance). It also explicitly differentiates from the homography sibling for the pattern's outline, so an agent can distinguish it without opening the schema.

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 gives a clear use context ('see which parts of a pattern are present and where, even when the pattern is scaled or rotated') and routes to /v1/homography for outlines. However it never mentions the template-match sibling, which is the most likely alternative for a matching task, leaving a gap in when-not-to-use 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?

No annotations are provided, so the description carries the full burden, and it does well: it discloses the algorithm, the complete return payload (found flag, 3x3 homography, projected corners, bounding box, inlier count as confidence), and the per-call cost of $0.004. It stops short of describing failure modes (e.g. what a found=false result implies) or error conditions on oversized/invalid inputs.

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 what the tool does and what it returns, followed by the use case and price. No filler, no restatement of the title, and every clause carries information an agent needs.

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 and no annotations, the description compensates well by enumerating all returned values, stating the algorithm, and quoting cost. The remaining gaps are minor: no explicit note about behavior on failure to find the pattern, and no alternative-tool routing guidance for a tool with two closely named siblings.

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 the baseline is 3 and the schema does the heavy lifting for all seven parameters. The description still adds meaning beyond the schema by tying 'inlier count as confidence' to the min_inliers threshold and by framing the detector choice and RANSAC homography as the core pipeline, which helps an agent reason about the knobs rather than just fill them in.

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 ('Locate a pattern image inside a larger image') plus the technical mechanism (ORB/SIFT + cv2.findHomography with RANSAC), and the qualifier 'even when it is scaled, rotated or viewed at an angle' functionally differentiates it from a plain template matcher. However, it never names the sibling tools (feature-match, template-match), so the routing decision is left to inference.

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 provides clear application context with 'Use it to find a UI element, logo or object in a screenshot or photo', and the 'scaled, rotated or viewed at an angle' condition implicitly states when this is preferred over a rigid template matcher. There is no explicit when-not guidance and no mention of the sibling tools as alternatives.

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?

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.