Kelvin — power electronics components

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for going further: it discloses the two-stage mechanism (pre-gating at reject edges, then scoring on value/ratings/footprint/mount type) and a real output caveat that incomplete source specs can never yield a clean 'recommended'. It stops short of describing result volume or how ties/near-misses are surfaced.

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 front-loaded sentences that lead with purpose, then mechanism, then the caveat — a logical order with little waste. 'The ... cross-reference the Kelvin web app runs' is slightly ornamental and the packet is dense, but every clause contributes.

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 zero schema descriptions, no output schema, and no enums, the description omits the required `family` argument and all filtering/limiting semantics. An agent knows the intent but not how to construct a correct call or what shape of result to expect.

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 0% across six parameters, so the description carries the full burden and fails: `family` is a required parameter that is never mentioned, and `same_type`, `max_results`, `manufacturer` and `target_manufacturers` are entirely unexplained. The listed dimensions (value, ratings, footprint, mount type) are scoring criteria, not inputs, so they do not compensate.

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: 'Find substitutes for a part by MPN', plus the distinctive framing that this is the deterministic, program-only path rather than an LLM-driven one. That implicitly separates it from recommend_parts, but the sibling is never named, so differentiation is inferred rather than explicit.

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 'deterministic, program-only ... No LLM judgement' phrasing implies when to pick this over a generative recommender, and the note about incomplete originals implies when results will be weak. However, no alternative tool is named and there are no explicit use/don't-use conditions for the sibling set.

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, closed-world and non-destructive, so the safety profile is covered. The description adds useful content about what the call reveals (filter/sort/bucket fields and designRequirements selector keys). It does not say what happens for an unknown or misspelled family, which is the main behavioral unknown for an introspection call.

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: the first states what comes back, the second states when to call it. No filler, no restating the title, and the payoff is front-loaded.

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, the description does a reasonable job sketching the return contents, but it leaves the family identifier format undefined and never points at list_families for name discovery. For an introspection tool whose whole value is knowing valid names, that gap matters.

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 0% for the single required 'family' parameter, so the description carries the burden of explaining what a family is. It uses the term but never clarifies whether 'family' is a name sourced from list_families, an ID, or a path. Baseline 3 for a one-parameter tool with an unresolved identifier question.

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 the exact artifact returned: the field names a family can be filtered, sorted and bucketed on, plus the designRequirements keys its selector reads. That is a specific, verifiable scope that separates it from search_parts or part_details. The verb is implied by the title ('Describe') rather than stated, which keeps it just 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?

It gives an explicit trigger ('before search_parts on an unfamiliar family') and an explicit anti-pattern ('rather than guessing field names'). What it omits is the other obvious alternative: how to discover valid family names in the first place (list_families), and what to do for families already familiar.

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 annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so safety is covered. The description adds useful return-content context (part counts and deterministic selector), but it does not mention ordering, pagination, or response format.

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 compact sentences cover the catalogue scope, returned information, and entry-point role with no wasted text. The key information is front-loaded.

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 parameters, no output schema, and rich annotations, the description supplies enough context to invoke the tool correctly: it explains what families are listed and what each entry includes. No additional invocation details are required.

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?

This tool has zero parameters, so there are no parameter semantics for the description to clarify. Per the rubric, a zero-parameter tool receives a baseline of 4.

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 that this returns every component family in the TAS catalogue and specifies the included attributes (part count and deterministic selector). 'Start here' hints at its entry-point role, though it does not explicitly name the sibling tools it should precede.

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?

'Start here' gives a clear workflow cue for when this tool should be used first. It does not state when-not to use it or explicitly route to alternatives such as describe_family or search_parts.

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 annotations already establish that this is a safe, idempotent, read-only operation, so the description does not need to repeat that. It adds useful return-context by naming extracted specs and optional catalogue data such as datasheet URL and provenance, but it does not clarify how the optional record is controlled or what changes when it is omitted.

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 a single front-loaded sentence with no wasted text. It communicates the core lookup and the optional return depth efficiently.

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 and no schema parameter documentation, so the description should do more. It gives a good high-level sense of the return value, but omits required family semantics, manufacturer usage, and include_record behavior, leaving meaningful gaps for a 4-parameter 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 0%, so the description must carry the burden for 4 parameters. It mentions MPN and the optional full catalogue record, but leaves the required family parameter and the optional manufacturer parameter completely unexplained, and does not state include_record's default or effect.

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 identifies the resource as a single part looked up by MPN and states what it returns: extracted specs plus an optional full TAS catalogue record. It distinguishes itself implicitly from sibling search/list tools by focusing on one known MPN, though it does not name a sibling explicitly.

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?

Usage is implied: use this when you already have a specific MPN and need its specs or catalogue record. The description does not state when not to use it or explicitly route the agent to search_parts, cross_reference, or other 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?

Goes beyond the readOnly/idempotent annotations by disclosing the selection mechanism (deterministic, no LLM judgement, reproducible) and that output carries the margins that drove ranking. It does not cover what 'options' or 'include_envelope' change in behavior, but the core behavioral character of the selector is clear.

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 operative clause is front-loaded and tight, but 'Kelvin's deterministic selector' and 'Same authority Kirchhoff and Heaviside select through' are persona branding that consumes roughly half the text without helping an agent invoke 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?

A five-parameter tool with nested objects, 0% schema coverage, and no output schema needs the description to explain the shape of the requirements block and the effect of options/envelope. The description leaves both the input shape and the return structure largely unspecified.

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 0% across five parameters including two nested objects, and the description only gestures at 'requirements' as a designRequirements block. The 'family', 'options', 'max_results', and 'include_envelope' parameters are left entirely unexplained, so the coverage gap is not compensated.

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: 'rank real parts against a designRequirements block' and states what comes back ('candidates with the margins that ranked them'). It never names a sibling (search_parts, cross_reference) to draw the boundary, so differentiation has to be inferred from the word 'rank'.

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?

Implies usage by requiring a 'designRequirements block', which suggests this is the tool for constraint-driven selection rather than free-text lookup. It gives no explicit when-not conditions and no alternative named, so an agent choosing between this and search_parts or cross_reference gets no routing help.

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 closed-world, so the safety profile is covered. The description adds that facet counts are optional and that search is scoped to a single family, but says nothing about pagination behavior, default/max result sizes, or the cost of enabling facets.

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 sentences, zero filler, with the core capability front-loaded and the disambiguating context trailing. Nothing is repeated from the schema or annotations.

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 output schema and zero schema documentation, the description is serviceable but incomplete: it does not tell the agent how to construct the filters/sort objects or what a result record contains. Adequate to choose the tool, thin for invoking it correctly on the first try.

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 0%, and the filters and sort parameters are free-form objects with additionalProperties true, so the description carries the whole burden — it usefully names the filter axes (numeric ranges, categorical, MPN substring, manufacturer) and with_facets. It never explains the shape of the filters dict, nor the meaning of sort, limit, or offset, so the gap is only partly closed.

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 — parametric search over one parts family — and enumerates the searchable axes (numeric ranges, categorical values, MPN substring, manufacturer). The clause 'this is the catalogue question ... and needs no converter design' hints at what it is not, but never names a sibling, so differentiation is partial.

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?

Frames the use case as the 'catalogue question' and rules out scenarios needing converter design, which is useful framing. However, no sibling is named (part_details, recommend_parts, cross_reference are all adjacent) and there is no explicit when-not guidance for choosing among them.

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, idempotent, non-destructive, closed-world behavior. The description adds return-content context not in the annotations: log vs linear bucketing and a count of parts that state the value at all, which helps the agent interpret output despite the missing output schema.

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 sentences, front-loaded with the core purpose, with the usage contrast appended. Slightly dense with em-dash clauses but every clause carries information; nothing is 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?

A five-parameter tool with no output schema and zero schema coverage needs more: the shape of filters, valid field naming, and bucket default behavior are left unexplained. It does describe the return semantics (bucket counts plus coverage count), which partially offsets the missing output 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 0%, so the description must compensate. It references all five params conceptually (family, field, log/linear, buckets, filtered slice), but gives no format details for filters, no constraint that field must be numeric, and no note on defaults.

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 operation: how a numeric spec is distributed across a filtered slice of a family, with bucket counts and a coverage count. It clearly delineates against list-style output ('what a top-N list cannot'), though it never names the sibling (search_parts/recommend_parts) that provides top-N lists.

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 a clear usage frame: answers 'what is available' questions rather than ranked retrieval. This contrasts with top-N tools implicitly, but there are no explicit exclusions or named alternatives, so the agent must infer which sibling to pick.

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