SafetyDataSheetAPI

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

Adds context beyond the annotations: billing per document from prepaid credit, failures not billed, API key requirement, and the returned confidence_score/warnings. Annotations already cover openWorldHint and non-idempotency, so this extra operational detail is meaningful and consistent with them.

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?

Front-loaded with the core action and output before secondary operational details. It is dense but every sentence carries information; no filler is present.

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 still sketches the return value (16-section record, confidence_score, warnings). Billing and auth are covered. Minor gaps remain around input size limits and processing time, but an agent has enough to invoke correctly.

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 all six parameters are already documented in the schema itself. The description only reinforces the file_url/file_base64 choice and adds no semantics for filename, language_hint, schema_version, or include_formats, 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 and resource ('Extract one Safety Data Sheet PDF') and describes the output shape (normalized 16-section record with confidence_score and warnings). The word 'one' implicitly separates it from submit_bulk_extraction, letting an agent pick the single-document tool 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 clear context for how to call it (file_url as public https URL or file_base64) and the cost model. It does not explicitly name submit_bulk_extraction as the alternative for batches, so routing guidance is implied by 'one' rather than stated.

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 and idempotentHint, so 'Read-only' is partly redundant. What earns credit is the disclosure of the auth model ('Requires a per-customer API key') and the fixed 30-day window, which the annotations do not cover.

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 sentence, front-loaded with the returned data, then two short clauses for scope, safety and auth. Every clause carries information; nothing is padding.

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 summarizes the return payload (balance, unit price, 30-day usage), which is what the agent needs. Minor gaps: no mention of what happens without a valid key or whether the 30-day window is fixed or configurable.

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 tool takes zero parameters, so there is nothing to document; baseline 4 applies. The description correctly leaves out any parameter discussion rather than inventing one.

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?

Uses a specific verb+resource ('get the prepaid credit balance, price per document, and the last 30 days of usage') and scopes it to 'the account that owns the API key'. This is unambiguously distinct from the extraction/bulk siblings without needing to name them.

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 only implied: the description states the account scope but never says when to call this (e.g., before submitting bulk extraction to check credit, or to monitor spend). No alternatives are named, though there is little overlap with extract_sds/get_bulk_job.

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 destructiveHint=false, so the bar is lower; the description still adds the authentication requirement ('Requires an API key') and that per-file results are returned, which annotations do not convey. 'Read-only and safe to repeat' largely restates the annotations, capping it below 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 short sentences, front-loaded with the purpose, then lifecycle context, then the auth prerequisite. No filler or restated title.

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 one parameter and no output schema, the description usefully characterizes the return value (status plus per-file results), which the agent would otherwise not know. It could say more about terminal vs. in-progress states or polling cadence, but nothing essential to calling it 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 coverage is 100% and the single parameter's schema description already explains it is the job_id returned by submit_bulk_extraction. The description adds no format, aliasing, or validation detail beyond that, so the 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?

Specific verb (get status and per-file results) plus precise resource (bulk extraction job) and explicit provenance link to submit_bulk_extraction. An agent can distinguish it immediately from extract_sds, get_account, and submit_bulk_extraction.

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?

States the job lifecycle position (a job created by submit_bulk_extraction), which tells the agent when to call it, and 'safe to repeat' signals polling is acceptable. It stops short of an explicit when-not or naming an alternative tool for cancellation/listing, so not 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?

Goes well beyond the annotations (which only give readOnly/openWorld/idempotent/destructive hints) by disclosing auth requirement ('Requires an API key') and the billing model ('reserved up front and released for any file that fails'). These are consequential traits an agent would not learn from structured fields alone.

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?

Four tight sentences, each front-loaded with the highest-value fact first (the async submit action), then workflow, idempotency, billing, and auth. Zero 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?

No output schema exists, but the description supplies the return value ('Returns a job_id') and the completion path via get_bulk_job, so an agent has everything needed to invoke and follow through correctly.

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 60%, and the description adds useful reinforcement of file_urls constraints (max 10, public https URLs) and idempotency_key retry semantics. However, it says nothing about callback_url, language_hint, or schema_version, leaving the two undocumented params unrecovered.

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 ('Submit'), resource ('SDS PDFs'), and scope ('up to 10... one asynchronous job'), which clearly distinguishes it from the sibling extract_sds (single) and get_bulk_job (polling). An agent can identify the tool's role without opening the 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?

Explicitly names the follow-up sibling ('poll get_bulk_job until status is completed or failed') and gives retry guidance ('Reuse the same idempotency_key when retrying'). The when-to-use and how-to-continue conditions are spelled out rather than inferred.

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