PartsTable

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

Annotations already declare readOnly, idempotent, closed-world behavior, so the safety profile is covered. The description adds provenance ('PartsTable read model') and signals that NSN/FSC fields may be absent ('when present'), which is genuine extra context, but it omits what happens when the part is not found — a key behavior for a lookup 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?

A single dense sentence with no filler: the verb and resource come first, followed by the returned field set and the data source. Every clause adds 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?

With no output schema, the description correctly compensates by enumerating the returned fields, giving the agent a clear picture of the response shape. The only gap is not-found/error behavior, which is minor for a simple single-parameter read.

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% with a single well-documented 'partNumber' parameter, so the schema carries parameter meaning. The description adds nothing beyond it regarding format, exactness, or normalization expectations (e.g., whether normalized PNs are accepted), so 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?

States a specific verb ('Get') and resource ('the part record') and enumerates the returned facets: identity, manufacturer, description, category, lifecycle, and NSN/FSC classification. This clearly separates it from sibling writes/validators, though it never explicitly differentiates from search-parts or get-substitutes.

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 tool is framed as a direct record lookup, which implicitly signals exact-part-number retrieval rather than exploratory search. However, no alternatives are named and there is no guidance on when to use search-parts or normalize-pn first, so the agent must infer the selection logic.

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 closed-world behavior, so the description's job is lighter. It adds genuinely useful context beyond the annotations: the results come from a cross-reference graph with a stated corpus size and a measurement date (2026-10-18), signaling a dated snapshot that may not reflect the latest data.

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?

A single front-loaded sentence with zero filler. The core action comes first and the supporting corpus statistics are parenthetical.

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 complete parameter schema and safety annotations, most needs are met. However, there is no output schema and the description does not indicate the return shape (e.g., list of part numbers vs. structured cross-references) or what happens when no substitutes exist, leaving a gap the agent must discover at call time.

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?

Only one parameter and schema coverage is 100%, with the schema itself describing 'Part number to find substitutes for'. Per the baseline rule for a single fully-documented parameter, no additional description text is required.

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 ('Find') and resource ('substitute / equivalent / cross-referenced part numbers') plus the data source (PartsTable cross-reference graph). It is clear what the tool does, but it does not explicitly distinguish itself from siblings like get-part or search-parts.

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 on when to use this versus get-part, search-parts, or normalize-pn, and no note on whether the part number should be normalized first. The synonym list ('substitute / equivalent / cross-referenced') is the only hint at matching scope.

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, idempotentHint=true, and openWorldHint=false, so the safety and determinism profile is covered. The description adds the concrete format families it recognizes, but is silent on behavior for unrecognized or malformed input (error vs. pass-through) and on output shape, which are the meaningful remaining unknowns.

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 short sentences, front-loaded with the verb and resource, followed by supported formats and rationale. No filler or 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 a single-parameter, non-destructive, idempotent transformation with no output schema, the description covers purpose, scope of formats, and motivation. The only meaningful gap is failure behavior for unrecognized part numbers, which an agent would want to know before calling.

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?

Only one parameter and schema description coverage is 100%, so the baseline is 3. The vendor format examples in the description indirectly illustrate what the partNumber string may look like, but add no syntax, casing, or separator rules beyond 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?

States a specific verb and resource ('Normalize an IT hardware part number into its standard form') and scopes it with the vendor formats handled (HPE, Dell, IBM/Lenovo). It does not explicitly name or contrast with the close sibling validate-pn, so it falls short of full sibling differentiation, but the intent is unmistakable.

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?

'Critical for deduplication and accurate lookups' implies when to reach for it, but there is no explicit when-to-use/when-not guidance and no named alternative (e.g., validate-pn for checking validity without transforming). Usage must be inferred.

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 closed-world, so the safety profile is covered. The description adds value beyond that by disclosing the 25-item batch ceiling and clarifying that the tool reports existence per part rather than failing outright, though it says nothing about behavior on malformed or unknown part numbers.

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 with zero waste; the action and the batch cap are front-loaded and the return behavior follows immediately.

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 carries the burden of describing returns, and it does so at a high level (per-part identity summary plus existence flag). It is complete enough to invoke correctly, though the specific fields of the 'identity summary' remain 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?

There is only one parameter and schema coverage is 100%, with maxItems/minItems already encoded in the schema. The description restates the 25-item limit but adds no format, normalization, or duplicate-handling semantics 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?

States a specific verb and resource (look up part numbers against the PartsTable catalog), scopes it as a batch with a max of 25, and summarizes the return. It implicitly distinguishes itself from the single-part sibling get-part via the batch framing, but never names any 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?

The batch nature with a 25-item cap implies when this is preferable to a single-part lookup, but the description gives no explicit when-to-use/when-not guidance and never mentions get-part, get-substitutes, normalize-pn, or validate-pn 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?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds real context beyond them: the catalog is a closed, enumerated corpus of ~26.2M distinct part numbers with a measurement date, drawn from government, OEM and commercial sources, and it discloses what the response reports. It omits what 'structural validity' actually checks (format rules, checksums) and any latency or rate-limit expectations.

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?

One front-loaded sentence with the core action first and the catalog/return details trailing; nothing is redundant. The catalog-size parenthetical with a measurement date is slightly heavy for the value it adds, but it is informative rather than filler.

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 one-parameter, read-only validator this is close to sufficient, and the description sensibly states what is returned since there is no output schema. However, without an output schema the description should say more about the response shape — e.g. whether validity and existence are separate fields or a combined verdict — and the notion of 'structural validity' is left undefined.

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?

There is a single parameter with 100% schema description coverage, so the schema already does the documentation work and baseline 3 applies. The description adds nothing about input form — case sensitivity, whether dashes/spaces are tolerated, or whether the value should be normalized via normalize-pn first — which is exactly the guidance a validator would benefit from.

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 ('Validate a part number') and clarifies the two-part outcome: structural validity plus catalog existence. It also names the backing catalog (PartsTable) and its source authorities, which distinguishes it conceptually from get-part and search-parts. It stops short of explicitly contrasting itself with the siblings, so a 4 rather than 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 use case (checking whether a part number is well-formed and present before doing something else) is implied by 'validate' and 'check whether it exists', but there is no explicit when-to-use statement, no exclusion, and no routing to siblings like normalize-pn or get-part. An agent must infer whether to normalize first or to call this before or after a lookup.

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