PartsTable

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

With no annotations, the description carries the transparency burden. It adds useful context by naming the data source (PartsTable canonical read model) and notes that classification is returned 'when present.' However, it does not disclose behavior like read-only status, error handling, or query limits, leaving gaps typical of a minimally adequate description.

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 two sentences, front-loaded with the core action ('Get the canonical record') and wastes no words. It lists fields and source 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?

For a simple single-parameter lookup with no output schema, the description conveys the record scope, source, and optional classification field. It lacks explicit mention of not-found behavior or return format, but these are minor for a straightforward read tool, making it nearly complete.

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%: the only parameter, partNumber, is already described as 'Part number to look up.' The tool description adds no further parameter semantics, so the baseline score 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?

The description clearly states the tool's function: retrieve the canonical record for a part, listing specific data fields (identity, manufacturer, description, category, lifecycle, NSN/FSC). This distinguishes it from siblings like search-parts (searching) or get-substitutes (alternatives).

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 context of 'canonical record' and 'canonical read model' implies this is the authoritative exact-match lookup, giving clear usage context. However, it does not explicitly mention when not to use it or contrast with siblings, so it misses the explicit exclusions that would merit a 5.

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?

No annotations are provided, so the description carries the full burden. It implies a read-only lookup from a specific graph with 591K+ pairs, but does not disclose return format, error handling, or case sensitivity. For a simple tool this is adequate but not thorough.

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 words. It clearly states the action, resource, and relevant context (source and scale).

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?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description covers core purpose and source well. However, it does not specify the output format, which would be helpful for an agent without an 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 100% (the parameter has a description). The tool description adds meaningful context: 'from the PartsTable cross-reference graph (591K+ verified pairs)', which enhances the schema by specifying the data source and scale.

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-resource pair ('Find substitute / equivalent / cross-referenced part numbers') and clearly distinguishes this tool from siblings like get-part (retrieve part details) and search-parts (general search).

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 lacks explicit guidance on when to use this tool versus alternatives like search-parts or get-part. It does not provide any exclusion criteria or usage context beyond stating the data source.

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?

No annotations are present, so the description carries the full burden. It conveys the transformation behavior and supported formats, but does not disclose what happens for unsupported inputs, the exact canonical format, or the return value structure, leaving some behavioral ambiguity.

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 three concise sentences, each serving a distinct purpose: defining the action, listing supported formats, and identifying the use case. There is no redundancy or 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 simple one-parameter normalization tool without an output schema, the description covers purpose, formats, and use case. It does not specify error handling for invalid inputs or the return format, but these gaps are not critical given the tool's simplicity.

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 schema only states 'Part number is required' with minimal detail, while the description adds meaningful semantics by indicating the input can appear in HPE, Dell, or IBM/Lenovo formats. This helps the agent understand acceptable input formats 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?

The description clearly states the tool normalizes an IT hardware part number into its canonical form and explicitly lists the supported vendor formats (HPE, Dell, IBM/Lenovo). This distinguishes it from siblings like validate-pn or get-part, which have different purposes.

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 notes that normalization is 'critical for deduplication and accurate lookups,' giving clear context for when this tool is useful. It does not explicitly name alternatives or exclusions, but the use case is well implied.

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?

No annotations are provided, so the description carries the full burden. It correctly indicates a read-only lookup operation by stating 'Look up' and describing the return. However, it lacks disclosure of potential error handling, partial results, or any authorization requirements. The description is honest but could add more behavioral context.

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 consists of two concise sentences with no wasted words. It front-loads the core action 'Look up a batch of part numbers' and immediately adds the batch limit and output summary. Every sentence is informative.

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?

Given the tool's low complexity (one required parameter, no output schema, no annotations), the description covers the essential purpose, input, batch limit, and output nature. It does not address error behavior or response format, but for a straightforward search tool, it is reasonably complete.

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% since the only parameter 'partNumbers' has a description. The tool description adds value beyond the schema by explaining that it processes a batch, sets the maximum size, and describes the output (per-part summary and existence). This goes beyond the baseline of 3 for high coverage.

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 verb 'Look up a batch of part numbers', the resource 'PartsTable catalog', and the output 'per-part identity summary and whether each exists'. It also specifies the batch size limit of 25, which distinguishes it from sibling 'get-part' (likely single-part lookup).

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 use for batch part number lookup and mentions the size limit, but does not explicitly state when to use this tool vs. siblings like 'get-part' for single parts or 'validate-pn' for validation. No alternatives or exclusions are given.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description states the tool returns structural validity and catalog existence, which is transparent about the two aspects of the result. However, it does not disclose side effects (likely none, but unstated), authentication requirements, rate limits, or whether the validation is case-sensitive or supports wildcards. It adequately conveys the core behavioral traits but leaves some details unspecified.

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 two sentences, front-loaded with the core action and followed by a concise result summary. Every sentence adds value, with no wasted words. It fits the standard pattern for effective tool descriptions.

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 only one simple parameter and no output schema, the description does enough by explaining the tool's purpose and result structure. However, it would benefit from briefly noting whether the tool is purely a read operation (likely) and what happens for invalid formats (e.g., error vs. false). Still, it provides sufficient context for the agent to use correctly given the tool's simplicity.

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%, meaning the schema already documents 'partNumber'. The description adds meaning beyond the schema by specifying that validation includes both structural checks and catalog existence against a large, multi-source database. This supplementary context helps the agent understand the part number matters and what type of lookup is performed, earning a score above the baseline of 3.

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 ('Validate') and resource ('part number'), clearly states the action of checking existence in the PartsTable catalog, and provides context about the catalog's scope (16M+ parts from multiple authority sources). The result dimensions ('structural validity and catalog existence') are explicitly named. This distinguishes it from siblings like 'get-part' (retrieval) and 'normalize-pn' (format conversion).

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 use for checking if a part number is valid and exists in the catalog. It does not explicitly state when not to use it or name alternatives (e.g., 'search-parts' for fuzzy lookups, 'normalize-pn' for format cleaning). However, given the single parameter and clear two-dimensional output, the context of use is sufficiently clear for the agent. A small loss for missing explicit when-not guidance.

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