Moltline Vision Maths

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes further by documenting the non-throwing error contract ({"error": ...}, with a concrete example), the typical input/output payload, and the retry-safety guarantee after correcting input. It also flags the silent-failure hazard (boxes that "quietly ruin every metric"), which helps the agent understand the cost of bad input.

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?

Front-loaded with purpose, then format semantics, then a concrete example, then routing rules and error behaviour — a defensible order. It is longer than strictly necessary: the paragraph on how the three formats disagree overlaps with the enum descriptions already in the schema, and the example return value duplicates what the output schema covers.

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 read-only, idempotent conversion tool with a full input schema and an output schema, the description supplies everything an agent needs: when to call it, what the payloads look like, how failures are surfaced, and that retries are safe. No gap is left that the structured fields don't cover.

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 parameter documentation is already strong. The description adds a worked example that shows all five meaningful fields in use together (including the image_width/image_height requirement when YOLO is on either side), which is more than restating the schema. It stops short of explaining the `clip` flag's behaviour, which is left entirely to the schema.

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 specific verb and resource ("Convert bounding boxes") and enumerates the exact three formats involved, so an agent knows the operation's scope immediately. It also names the sibling tools it is not (detection_metrics, nms), making it distinguishable without opening any 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?

States the triggering condition ("whenever a dataset and a model disagree about format") and explicitly excludes two sibling tools by name with their purposes. Nothing is left for the agent to infer about when to route here.

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, so restating "read-only and idempotent" earns nothing. The genuinely additive disclosure is the error contract — it never raises a protocol error and instead returns {"error": ...} — plus the claim that results match what a real accessibility audit reports. Those are useful, but the section is partly spent repeating structured fields.

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 core action and the exclusion list are front-loaded and easy to scan. The "FREE." fragment and the redundant restatement of the annotation flags are mild filler, and the worked example plus a separate error example is more illustration than most agents need, but nothing is misleading.

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?

An output schema exists, so return values need no prose explanation, and the annotations already cover the safety profile. What remains — the exclusion boundary, the error-not-exception contract, and the audit-matching precision claim — is all present, leaving no gap an agent would have to discover by trial.

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% and every property is documented inline, including the accepted hex variants and the 18pt/14pt-bold rule for large_text, so baseline 3 applies. The worked input/output example reinforces the input format but adds no semantics the schema doesn't already carry, and large_text's effect on the returned thresholds is only implied by the example's "required" block.

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?

States a specific verb and resource — "Check a colour pair against the WCAG contrast thresholds" — and immediately binds it to a concrete computation (WCAG 2 relative-luminance). It also excludes adjacent purposes (colour-space conversion, palette generation), so an agent can tell it apart from anything else in the toolset 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?

"Use when generating or auditing an interface" gives a positive trigger, and "Not for converting colours between spaces and not for palettes" gives explicit negatives. The error contract adds the recovery path (correct input, then retry), which is the remaining thing an agent needs to know to use it safely in a loop.

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 cover read-only, idempotent and non-destructive, but the description adds material context beyond them: a PREMIUM license gate, the matching algorithm and AP interpolation convention, and critically the error contract (never raises a protocol error, returns an {"error": ...} object with a fix hint) plus the retry-safety implication. That error-shape disclosure is exactly the kind of behavioral detail annotations cannot express.

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?

Front-loaded with purpose and protocol, then example, then usage guidance, then error contract — a sensible ordering. The inline example is long but the tool has no output schema documentation burden elsewhere and it disambiguates the array-of-objects params, so it largely earns its space. Minor deduction for the awkward 'PREMIUM (license).' sentence fragment interrupting the opening line.

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 scoring tool with six parameters, nested-free schema, full schema descriptions and an output schema, nothing an agent needs is missing: input shape, algorithm, metric definitions, error behavior, retry safety, and the sibling to run first are all present.

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 the baseline is 3. The description earns an extra point by giving a concrete worked input showing the actual shape of predictions entries (box/label/score with a 0.9 confidence) and the ground_truth entries, and by tying iou_threshold to the matching behavior rather than only to a range. It does not cover box_format or the yolo image_width/height requirement, which the schema handles.

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?

States a specific verb and resource ('Score detections against ground truth') and immediately pins down the protocol (greedy matching, IoU threshold, highest-confidence first) plus the reported metrics (per-class precision/recall/F1, VOC-2010 all-points AP). No sibling tool does evaluation, and the description explicitly carves out nms as a separate prior step, so the boundary is unambiguous.

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?

'Use to compare two models on the same held-out set' gives a positive selection criterion, and 'Not for cleaning up a single model's overlapping output first - run nms before this' gives an explicit exclusion naming the sibling to use instead. This is the when/when-not/alternative pattern at full strength.

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 readOnly/idempotent/non-destructive, but the description adds material context: nothing is decoded, a base64 prefix suffices, and errors come back as {"error": ...} rather than protocol errors, making retry-after-correction safe. That is behavioral information annotations cannot express.

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?

Front-loads the core capability and the 'FREE' cost cue, then groups usage and error behavior cleanly. The inline input/output JSON examples are verbose but earn their place by making the prefix-only contract concrete.

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?

An output schema exists, so return values need no explanation, yet the description still shows the shape. Size limits, error contract, and read-only idempotency are all covered, leaving nothing an agent needs 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 coverage is 100%, so the baseline is 3; the description goes further by stating that only a base64 prefix is needed and by showing a concrete input example. The remaining details (data-URL stripping) live in the schema rather than the description, so it does not fully extend the single parameter.

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?

States a specific verb and resource: 'Read an image's format and pixel size from its header alone,' plus the supported formats (PNG, JPEG, GIF, BMP, WebP). It is clearly distinguishable from siblings like resize_plan and colour_check, which the description implicitly excludes ('before planning a resize', 'nothing here reads pixels').

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 explicit when-to-use ('Use to find out what you are dealing with before planning a resize') and explicit when-not ('Not for pixel content ... and not for EXIF'). This is exactly the routing information an agent needs against sibling tools.

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 readOnly/idempotent/non-destructive, and the description goes well beyond them: it documents the tie-breaking rule and determinism guarantee, the premium license requirement, and a precise error contract (never raises a protocol error; returns {"error": ...}) plus the safe-retry implication. These are exactly the behavioral traits annotations cannot express.

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?

Front-loaded with purpose and algorithm, then example, then usage and error handling — a sensible order with little filler. The sample return value partly duplicates the output schema, which is the only reason it falls short of a 5.

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 6-parameter algorithmic tool with a full output schema, the description covers purpose, algorithm, determinism, licensing, error behavior, and sibling routing. Return values are explained by the output schema, so the example is a bonus rather than a gap-filler; nothing an agent needs to call this correctly is missing.

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 the baseline is 3; the description earns more by supplying a concrete worked input and by surfacing a cross-parameter constraint the schema cannot state ("boxes and scores must be the same length"). It does not mention box_format, image_width/height, or the meaning of iou_threshold beyond "the threshold", leaving those entirely to the schema.

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 specific verb and resource ("Remove duplicate detections of the same object") and immediately names the algorithm (greedy non-maximum suppression) so an agent knows exactly what operation this is. It also distinguishes itself from the siblings bbox_convert and detection_metrics by name, so no schema inspection is needed to tell them apart.

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?

"Use after a detector that emits overlapping boxes" gives a positive trigger, and "Not for scoring against ground truth (detection_metrics) and not for format changes (bbox_convert)" gives explicit exclusions mapped to the correct alternatives. This is a full when/when-not/alternative routing statement.

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 readOnly, idempotent and non-destructive, yet the description adds a genuinely non-obvious contract: invalid input never raises a protocol error but returns an {"error": ...} object, and retry after correction is always safe. The retry sentence partly restates the idempotentHint, which keeps this from a 5, but the error-shape disclosure is real added value.

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?

Front-loaded with purpose, then usage, then error behavior - a sensible order with no filler paragraphs. The standalone "FREE." token and the verbose rendered example are the only parts that cost space without adding decision-relevant information.

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?

The tool is non-trivial (5 params, presets, three modes) and the description covers when to call it, what the output means for downstream box transforms, and the exact error contract. An output schema exists, so return values need not be explained, yet the example still orients the agent.

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 per-tool baseline is 3, but the worked example ({"width": 1920, "height": 1080, "target": "yolo_640"} -> scale/resized/pad/box_transform) concretizes what width, height and target actually produce and shows the default target in action. It does not add anything about mode or target_size beyond the schema, so it stays below 5.

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?

States a specific verb and resource: compute the exact scale, padding and crop for a model input size. It also names what it is not (image_probe) so an agent can separate it from the closest sibling without opening either 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?

"Use before feeding an image to a fixed-input model" gives the trigger condition, and "Not for finding out the image's size in the first place - that is image_probe" gives an explicit exclusion plus the alternative tool by name.

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