Balford metalworking engineering answers

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

Goes well beyond the annotations (readOnlyHint/openWorldHint/idempotentHint): it discloses that answers are grounded only in public balford.net material, carry numbered citations with source pages, and that the tool will refuse pricing, lead-time guarantees, unheld certifications, and customer-drawing content. It also disclaims that output is not a quotation, certification claim, or dimensional acceptance — exactly the behavioral context an agent needs before relying on the result.

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 and usage are front-loaded well, but the text is repetitive: 'Returns a written answer with numbered citations plus the source pages' is restated later as 'Answers are assembled from Balford's own published engineering material and cite the page each claim came from,' and the public-source constraint is stated three times. Several sentences do not earn their place, which is what keeps this below a 4.

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 an output schema present, annotations covering the safety profile, and 100% schema coverage, the description supplies everything left: domain scope, grounding rules, citation behavior, and explicit refusal boundaries. Nothing an agent needs in order to call and interpret this tool 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 description coverage is 100% for both parameters (question with maxLength 600, lang with BCP-47 default 'en'), so the schema already carries the parameter semantics. The description adds nothing about the parameters themselves, so the baseline 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?

States a specific verb+resource: 'Answer a metalworking engineering or sourcing question from Balford's own published engineering material.' The Q&A framing is unmistakably different from the sibling tools list_engineering_topics and search_balford_material, and the scope (fine blanking, ironing deep drawing, tolerances, DFM, RFQ prep) is enumerated so an agent knows the domain without opening a 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?

Gives explicit when-to-use phrasings ('how do I', 'what is', 'which process fits', 'what do you need for an RFQ') and explicit when-not boundaries (no price, no lead-time guarantee, no certification it does not hold, nothing from a customer drawing). Alternatives are not named by tool, but the trigger conditions and exclusions are specific enough that routing is unambiguous.

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 safety is covered. The description adds genuinely new operational context — 'Costs no model tokens' — which informs the agent's cost trade-off against the sibling tools. It doesn't mention pagination or result-size limits, hence not a 5.

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 with zero filler: what it returns first, then when to use it, then the cost note. Front-loaded and appropriately sized for a simple list 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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The only gap is that the optional category filter is absent from the description, leaving the agent to discover filtering from the schema alone.

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 description never mentions the optional 'category' filter. With schema description coverage at 100%, the schema fully documents the parameter (including case-insensitive matching and examples), so the baseline 3 applies — the description adds nothing but loses nothing.

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 ('List the canonical engineering questions Balford's knowledge base is built around'), plus scope ('grouped by process family') and payload ('URL of the answer page'). This is clearly distinct from ask_balford_engineering and search_balford_material.

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 usage context: 'find the right published answer before asking a free-form question' and 'see whether a topic is covered at all'. It gestures at the alternative (free-form question) but never names ask_balford_engineering or search_balford_material, so routing still requires inference.

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?

Adds substantial context beyond the annotations: no model-token cost, results are assembled only from Balford's own published material, each claim cites its source page, and nothing non-public is quoted. It also declares scope boundaries ('not a quotation, a certification claim, or a dimensional acceptance'), which the readOnly/openWorld/idempotent hints do not convey.

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?

Well front-loaded: purpose first, then use cases, then cost and provenance. The final boundary sentence ('not a quotation, a certification claim, or a dimensional acceptance') is denser and more defensive than an agent needs for invocation, but the overall length is reasonable and nothing is redundant.

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-value shape need not be explained. Combined with the cost note, sourcing guarantee, and citation behavior, an agent has everything needed to decide to call this tool and to interpret and trust its output.

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%, with both 'limit' (range and default) and 'query' (with examples) fully documented in the schema. The description adds no syntax, format, or query-construction guidance beyond that, 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?

States a specific verb and resource ('Retrieve the passages of Balford's published engineering material that match a query') and immediately scopes it against the answering sibling with 'without writing an answer.' An agent can distinguish this from ask_balford_engineering 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?

Gives three concrete use cases: checking what has actually been published, gathering source URLs for citations, and grounding reasoning. The 'without writing an answer' clause implies the alternative answering tool, but no sibling is named explicitly as the recommended route for the opposite case, so it falls just short of full when/when-not routing.

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