anteroom

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

With no annotations provided, the description carries the full burden. It states what is returned, but does not explicitly confirm read-only nature, potential rate limits, or pagination behavior. For a simple retrieval tool, this is acceptable but not fully transparent.

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 main action and quickly elaborating on return contents. Every word earns its place with no redundancy.

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 list-retrieval tool with no output schema, the description covers the essential information: what the tool does, what it returns, and how to specify the lab. It lacks only minor details like response format or error handling, but these are not critical for this 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 input schema fully describes the only parameter (lab_slug) including allowed values, meeting the 100% coverage baseline. The description adds no further parameter detail, so a baseline score of 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?

The description uses a specific verb ('Get') and resource ('full version ledger of a frontier AI lab's safety framework'), clearly differentiating from sibling tools focused on partnerships and vendor commitments. It also lists example frameworks and the output fields, leaving no ambiguity.

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 when to use the tool is clear: whenever you need version history of a lab's safety framework. However, it doesn't explicitly mention when not to use it or reference alternatives, though the sibling tools are distinct enough that no confusion is likely.

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 discloses the return contents in detail, which is valuable for a read-only getter. However, it doesn't mention error handling (e.g., unknown slug) or any side effects. Given the low-risk read nature, this is adequate and adds context beyond a bare 'Get pattern'.

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 that states the action and enumerates the result components. Every phrase contributes to understanding what the tool returns. No filler or repetition of schema details.

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 tool with no output schema, the description is reasonably complete: it lists all the elements returned and the parameter is fully documented. However, it lacks explicit guidance on when to use this tool versus siblings, and the absence of an output schema means the description's list must suffice. It could mention behavior for unknown slugs, but that is a minor gap.

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 descriptive property and examples. The description adds little beyond calling the pattern 'named', which ties to the pattern_slug. Per calibration, baseline is 3 when schema fully documents parameters, and the description does not compensate or go beyond it.

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 tool as retrieving a named pattern, enumerating its contents (plain-language description, example clauses, kill-list moves, scholarly anchors, precedent anchors). This distinguishes it from siblings like get_partnerships_by_pattern, which likely returns partnerships matching a pattern rather than a single named pattern.

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 explicit when-to-use guidance or alternative references. The description implies this tool is for fetching a specific pattern by slug, but it doesn't say when to prefer it over get_partnerships_by_pattern or search_corpus. This is typical of a simple getter but falls short of the 4 or 5 standard.

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?

With no annotations, the description carries full transparency burden. It discloses that this is a listing operation returning metadata and a permalink to a primary-source-anchored deal page, which is meaningful context. It does not explicitly state read-only behavior, but 'List' implies no mutation; the lack of side effects is consistent.

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 that clearly states the action, scope, and return value. No wasted words or redundancy—it is a model of conciseness.

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 simple nature (2 params, no output schema, no annotations), the description is complete: it explains what is returned, the filtering criterion, and the source integrity. The schema covers parameter details, so the description fills the remaining gaps effectively.

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 both parameters already described in the input schema. The tool description adds no additional parameter semantics beyond what the schema provides, matching 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 the specific verb 'List' and clearly identifies the resource: 'every tracked public AI strategic partnership' filtered by a pattern. This distinguishes it from siblings like get_partnership_pattern, which likely returns patterns themselves, and makes the purpose 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?

The description implies when to use it (when you need partnerships matching a pattern) but does not explicitly state alternatives or exclusions. The schema mentions get_partnership_pattern for finding pattern slugs, but this is not in the description text, so guidance is limited to 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?

With no annotations, the description carries the full burden for behavioral disclosure. It explains the return value structure (quoted text, URL, effective date) and the verb 'Get' implies a read-only operation. It does not explicitly state 'no side effects,' but the tone and content are sufficient for a simple retrieval 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?

The description is only two sentences. The first sentence states the core purpose and lists all seven commitments; the second explains what each carries. Every word adds value, with no redundant phrasing.

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 tool with one parameter, no output schema, and no annotations, the description is remarkably complete. It enumerates the exact commitments and return fields, so the agent knows what to expect and what inputs are needed. No critical information 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?

The schema describes vendor_slug with its allowed values, and the description adds no additional parameter information. Given 100% schema coverage, the baseline of 3 applies; the description neither improves nor worsens parameter clarity.

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 the specific verb 'Get' and identifies the resource as 'the seven tracked commercial commitments' with an explicit list (AUP, no-train default, etc.). This clearly differentiates it from sibling tools like get_framework_version_history and get_partnership_pattern, which target different data.

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 gives clear context by stating it applies to 'a frontier AI vendor' and specifies exactly what data is retrieved. It does not explicitly name alternatives or exclusions, but the purpose is well-scoped enough for an agent to know when to use it, given the distinct sibling tools.

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?

With no annotations provided, the description carries the full burden for behavioral disclosure. It adds useful context about return values (primary-source URLs and confidence tags), but lacks details on ordering, potential side effects (though unlikely for a search), or any access requirements, leaving some gaps.

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 with the first leading with the action and scope and the second stating the output. It is front-loaded, concise, and contains no unnecessary details.

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?

The description covers the tool's purpose and output, while the schema covers parameters, resulting in a fairly complete picture. However, without annotations or explicit usage guidance, a note about it being a read-only search or result ordering would make it fully 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?

The schema already provides 100% coverage, including descriptions for all parameters, examples for jurisdiction and lens, and a default for limit. The description adds context about the corpus and legal lenses but does not significantly enrich parameter understanding 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 searches 'Anteroom's tracked corpus of AI-relevant regulatory provisions' with a specific verb and resource. It also distinguishes from sibling tools (which handle framework history, partnerships, and vendor commitments) by emphasizing its search and corpus nature.

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 provides clear context about what the tool does and its scope across jurisdictions and lenses, but does not explicitly mention when to use it over alternatives or when not to use it. The context is enough to infer its intended use, but no exclusions or alternative suggestions are given.

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