MVisionPro Engineering Tools

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

Annotations already declare readOnlyHint=true, openWorldHint=false, and idempotentHint=true, so the safety profile is covered. The description adds useful constraints: the competitor model must be 'unambiguous' and the candidate set is 'bounded' and 'public', which gives additional context beyond annotations. It does not mention output format or error behavior, but the annotation coverage lowers the burden.

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 repeats essentially the same sentence twice with minor rewording ('bounded Hikrobot candidates' vs 'bounded set of public Hikrobot candidates'). This redundancy is unnecessary and not efficient; a single sentence would have been clearer and more concise.

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 has no output schema, and the description does not state what the comparison returns (e.g., list of matches, similarity scores), how 'bounded' is enforced beyond the limit parameter, or how ambiguity in the competitor model is handled. Given its simplicity and annotation coverage, the description is minimally adequate but leaves notable gaps for correct invocation.

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% because all three parameters (q, lang, limit) have descriptions in the schema. The description itself does not add parameter-specific semantics beyond the schema; the phrase 'unambiguous' hints at the q requirement but is not directed at parameter syntax or formatting.

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 clearly states a specific verb ('Compare') and resource ('competitor model' with 'Hikrobot candidates'), and the title 'Camera cross-reference' reinforces the domain. However, it does not explicitly differentiate from sibling tools, though the operation seems distinct. The duplication does not add confusion.

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?

No explicit guidance on when to use this tool versus sibling tools, nor any exclusions or prerequisites. The description implies a scenario (having a competitor model and wanting Hikrobot matches) but does not state it as a clear instruction or reference 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds valuable behavioral context beyond that: it discloses rejection behavior for partial manual sets and mixed camera/manual inputs, which the schema alone does not fully convey. It does not contradict annotations — a read-only calculation that rejects invalid inputs is consistent.

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?

Purpose is front-loaded in the first sentence. The description is long, but every sentence earns its place given the intricate oneOf/alias constraint logic — removing any clause would lose critical validation information. It is dense rather than padded.

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 13-parameter tool with a complex allOf/oneOf schema and no output schema, the description is remarkably complete. It covers the two input modes, alias rules, rejection behavior, and exclusivity constraints. Minor gaps: it does not describe the return format or explain optional fields like interface, camera count, cable length, and language — though these are documented in the schema.

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. The description adds meaning beyond the schema by explaining the alias relationships (width/widthPx, height/heightPx), that mixed alias pairs are accepted, that both aliases for one axis must not be sent, and the exclusivity between camera and the manual set. This is genuine additional semantics over the per-field descriptions.

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-resource pair — 'Calculate stream bandwidth and evaluate interface options' — that clearly states the tool's function. It distinguishes itself from siblings (analog, linescan, models, optics, sensors) by describing a bandwidth-calculation/evaluation task rather than a hardware or model selection task.

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?

Extremely explicit. The description states the two mutually exclusive input modes (camera vs. complete manual set), gives the exact field requirements for each, forbids combining them, explains alias pairs and that mixed alias combinations are accepted, and specifies that both execution and discovery reject partial manual sets and every camera/manual mixture with a concrete example. No inference is left to the agent.

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 read-only and idempotent behavior, so the description only needs to add non-obvious behavior. It does so by explaining inference and defaulting rules: mode is inferred when omitted, and samplingMode defaults to xy, or to width when longitudinalStepMm is present. No contradiction with annotations.

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 dense sentences with no filler: purpose first, then required-and-exclusive input rules, then default behavior. Every sentence carries operational information an agent needs before calling the tool.

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 17-parameter calculator with a fully described schema, the description covers all non-obvious call rules: required width, one-of speed groups, one-of calculation groups, and mode/sampling inference. There is no output schema, but the first sentence states what is calculated, which is sufficient for this computation-style tool.

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; the description earns extra credit by consolidating exclusivity rules that are spread across the schema's allOf/oneOf structure. It clarifies that speedMmS and speedMMin are alternatives, that defectMm+nPx and accuracyMm+kPx form two calculation sets, and how mode/samplingMode defaults are derived. It does not annotate every parameter, but it covers the high-risk selection semantics.

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 ('Calculate') and concrete outputs ('line width, line rate, exposure and confirmed camera modes'). The name and title alone would not tell an agent this is a computation over width/speed/defect inputs; the description does. It also stands apart from the sibling tool names, which read as category filters rather than calculation tools.

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 gives clear operative rules: widthMm is required, exactly one speed field and one calculation set must be supplied, mode is inferred if omitted, and samplingMode defaults to xy or width depending on longitudinalStepMm. It does not explicitly name alternatives or when-not-to-use cases, but the constraints are strong enough to guide correct invocation.

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 openWorldHint=false, so the description only adds 'bounded public catalog projection', which signals limited scope. It does not add further behavioral context such as pagination behavior or authorization requirements.

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 fully redundant with the second, repeating 'Search the bounded public catalog projection'. The useful content fits in one sentence, so the duplication wastes the reader's attention.

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 search with fully documented parameters, this is adequate, but it does not describe what a result looks like or what 'bounded' means, and it never routes the agent to sibling tools when appropriate.

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%: q, lang, and limit are already described. The description mostly restates q's meaning ('literal model, alias, SKU or slug') and adds no format or precedence details beyond what the schema provides.

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 uses a specific verb ('Search') and names the resource ('bounded public catalog projection') plus the search keys (model, alias, SKU, slug). It is clear on its own but does not distinguish this tool from siblings like analog or optics; the phrase 'bounded public catalog projection' is repeated rather than explained.

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?

No guidance is given on when to use this tool versus sibling tools, no exclusions are stated, and there is no note on whether literal search is the intended mode versus fuzzy or alternative search. The reader must infer usage from the query-field description.

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?

The readOnlyHint and idempotentHint annotations already signal a safe, repeatable computation, and 'Calculate' is consistent with that. The description adds useful context beyond the annotations: the computed domains and the exclusive-sensor-source rule. No side effects or auth concerns need disclosing for a pure calculation tool.

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?

Two dense sentences with no filler. The verb and purpose are front-loaded, and the second sentence packs the critical constraints efficiently without repetition.

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 an 18-parameter calculation tool with a rich schema and safety annotations, the description supplies the missing interaction rules and the scope of what is calculated. A mention of output shape or units would make it fully complete, especially since no output schema exists, but the current definition is sufficient for correct invocation.

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. The description adds real value by restating the oneOf exclusivity in plain language and by adding the camera-versus-manual-passport-fields prohibition, which is not explicitly enforced in the schema for those fields. The undefined jargon 'manual passport fields' keeps this from a 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?

The description names a concrete verb ('Calculate') and a clear subject area: camera geometry, object sampling, exposure, and depth of field. This goes well beyond the title and gives an agent a specific sense of what the tool computes, though it does not explicitly contrast itself with siblings like analog or linescan.

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 gives explicit invocation constraints: exactly one sensor source must be provided, camera cannot be combined with manual passport fields, and fovMm and wdMm are always required. This is actionable and clear, but it does not explain when to prefer this tool over its listed siblings.

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=true and idempotentHint=true, and the description's 'Get' aligns with those. The description adds useful context about the exclusivity of lookup keys and the catalog scope, but does not reveal the response shape or any aggregation details beyond the name. No contradiction with annotations.

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?

Two short sentences, no fluff, with the core action and constraints front-loaded. The slight repetition of 'exactly one lookup key' is acceptable for emphasis.

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 lookup with fully described parameters and safety annotations, the description is nearly complete. It tells the agent what input to provide and what operation to expect; a small gap is that the returned 'sensor aggregation' is not described further, and there is no output schema to compensate.

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. The description reinforces the 'exactly one key' rule and clarifies 'catalog camera model' and 'sensor part number', but it does not add meaningful semantics beyond what the schema already states.

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 clearly states the operation ('Get a sensor aggregation') and the precise lookup resource (a catalog camera model or sensor part number). It does not explicitly differentiate from the sibling tools such as models or optics, so it stops short of a 5.

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 implies the usage context: call this when you have exactly one camera model or sensor part number. However, it provides no guidance on when not to use this tool or which sibling tool to prefer instead, leaving the decision to inference.

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