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

The annotations already provide readOnlyHint: true, so the read-only nature is known. The description adds behavioral context by specifying the type of data returned (metadata fields), which goes beyond the annotation. However, it does not mention response language behavior or potential limitations, so it's not a 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?

The description is a single, well-structured sentence that leads with the verb and object, then concisely lists the returned fields. Every word is informative with no redundancy, making it easily scannable for an AI agent.

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 responsibility for explaining return values, and it does so by listing the main metadata fields. It adequately covers the essential behavior for a simple read-only tool, though it omits details like response structure or error handling. Given the tool's simplicity and the provided schema, this is sufficiently 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 descriptions cover 100% of parameters, each with clear meaning (caseId from list_cases, language enum, databaseId example). The description adds no additional parameter semantics beyond what the schema already provides, so the 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 clearly identifies the resource ('metadata for a specific case') while listing the key fields returned (title, citation, decision date, keywords, URL). This differentiates it from sibling tools like get_legislation (which targets legislation) and get_case_citations (which returns citations) by focusing on case metadata retrieval.

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 usage when you need metadata for a specific case rather than a list (list_cases) or legislation (get_legislation), but it does not explicitly state when to use this tool versus alternatives. It lacks any exclusion criteria or direct reference to sibling tools, so guidance is only 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?

Annotations already provide readOnlyHint=true, and the description adds valuable behavioral context by noting that the API only supports English for this endpoint, with French requests falling back to English. This is beyond what annotations convey and helps set 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?

The description consists of two succinct sentences: the first states the tool's purpose, and the second adds a critical language constraint. Every word earns its place, with no fluff 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 read-only lookup tool, the description covers the core purpose and a key limitation. Although there is no output schema, the nature of citation data is self-explanatory, and the added language note addresses a potential edge case. A bit more detail on response structure would elevate it further, but current coverage is solid.

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 has 100% description coverage for all four parameters, including enums and examples. The description does not add additional parameter-level meaning beyond what the schema already provides, so the baseline 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 explicitly states 'Get citation information for a case' and enumerates the three types of data (what it cites, what cites it, legislation referenced), making the tool's purpose unmistakable. It clearly distinguishes from sibling tools like get_case or get_legislation by focusing solely on citation 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 provides a clear context for when to use the tool—when citation data is needed—but it does not explicitly name alternatives or when-not-to-use scenarios. This is clear guidance without exclusions, warranting a 4 rather than 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?

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds return-field details ('including title, citation, dates, and repeal status') which is useful context beyond annotations. However, it does not disclose any potential behavioral quirks like error handling, response format, or language-specific variations.

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 core purpose, omits any fluff, and includes the most relevant details about the returned metadata. It is optimally concise for an agent to parse quickly.

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 (3 params, no output schema), the description adequately explains the return content (title, citation, dates, repeal status). It covers the essential purpose and fields, though it could benefit from a note about using it after list_legislation, which is already hinted in the schema. The absence of an output schema makes the field enumeration valuable.

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%, with all three parameters (language, databaseId, legislationId) having clear descriptions. The tool description does not add any parameter-specific meaning beyond what the schema already provides, so it meets the baseline but does not exceed 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 states the tool's purpose: 'Get metadata for a specific piece of legislation' with a specific verb ('Get') and resource ('legislation'), distinguishing it from sibling tools like 'list_legislation' which lists multiple items. It also enumerates the key fields returned (title, citation, dates, repeal status).

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 context is only implied by the phrase 'specific piece of legislation' and the legislationId schema description referencing 'list_legislation'. There is no explicit statement about when to use this tool versus list_legislation or get_case, nor any exclusions. The example in the schema helps but the description itself lacks clear guidance.

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, and the description's 'List' wording is consistent. It adds scope context (all courts/tribunals, database IDs) but does not provide additional behavioral details like 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?

Single sentence, starts with the verb, contains zero filler, and fully conveys the operation in a clear front-loaded manner.

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?

Low complexity (one optional param), schema covers all params, readOnly annotation present, and description states the resource scope and output fields; no major gaps.

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 fully documents the single optional language parameter (100% coverage, enum en/fr, default en). The description adds no parameter-specific information, 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?

Description uses specific verb 'List' with resource 'courts and tribunals in the CanLII collection' and output 'database IDs', clearly distinguishing from sibling list_legislation_databases which covers a different resource.

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 guidance on when to use this tool versus list_legislation_databases or list_cases; usage is only implied by the clear resource scope. No alternatives or exclusions are mentioned.

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 declare readOnlyHint=true, and the description does not contradict this. The description adds a useful behavioral detail by stating that it returns case titles, citations, and IDs, but it does not disclose pagination behavior, default ordering, or how filters and offset/resultCount affect results. With read-only safety already covered by annotations, this is adequate but not rich.

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 short sentences with no filler. It front-loads the action and return value, making it easy to scan. Every word earns its place.

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 list endpoint with 8 parameters and no output schema, the description provides only minimal return-value information and no overview of pagination or filter combinations. However, the schema's 100% parameter descriptions and readOnlyHint annotation compensate for some gaps. It is minimally adequate but could benefit from mentioning how to page through results and the role of list_case_databases.

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 all parameters have descriptions. The tool description does not add additional parameter-level meaning beyond the schema; it only restates that decisions come from a specific database, which aligns with the databaseId parameter. Baseline 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 ('List') and identifies the resource ('decisions from a caselaw database'), and it mentions the returned fields (titles, citations, IDs). It is distinguishable from siblings like get_case or list_legislation, though it does not explicitly name an alternative as in the high-calibration example.

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 is provided about when to use this tool versus get_case, get_case_citations, or list_case_databases. The phrase 'specific caselaw database' hints that a databaseId is needed, but this is only fully spelled out in the schema, not in the description itself. No when-not or alternative tool is mentioned.

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 readOnlyHint annotation already communicates that this is a safe read operation. The description adds that it returns statutes or regulations, providing basic output context. It does not disclose pagination, ordering, or filtering behavior, but for a simple listing with annotations, this is adequate. No contradiction with annotations.

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 clear sentence, front-loaded with the verb and resource. It contains no redundant words and efficiently conveys the core purpose.

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 listing tool with two parameters, a clear description, and a readOnlyHint, the provided context is sufficient. The lack of an output schema is not critical since the name and description indicate a list return. The workflow dependency on list_legislation_databases is captured in the schema description, helping completeness.

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 both language and databaseId are already well-documented. The description's phrase 'from a specific legislation database' aligns with the databaseId parameter but does not add new semantic information beyond the schema. 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?

The description specifies the action (list) and the resource (statutes or regulations from a specific legislation database), clearly distinguishing it from sibling tools like list_legislation_databases (which lists databases) and get_legislation (which retrieves a single item). The phrase 'specific legislation database' signals the required databaseId.

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 context is implied by the required databaseId and the schema's reference to list_legislation_databases as the source of IDs. However, the description itself does not explicitly state when to use this tool versus alternatives like get_legislation, nor does it mention any exclusions. The guidance is present but only implicitly via schema.

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, and the description adds the behavioral detail that it lists 'all' databases, indicating a comprehensive response. It also specifies the collection scope ('CanLII'), giving the agent context about the data source, but does not detail output format or pagination behavior.

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, specific sentence with no filler, front-loads the action verb, and earns its place by clarifying the resource scope.

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 low complexity, presence of readOnly annotation, and complete schema coverage, the description sufficiently defines the tool's behavior for an agent. It lacks an output schema but listing tools typically return a simple list, and the description sufficiently scopes the return value.

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 provides full coverage for the single 'language' parameter, including enum values, default, and description. The tool description itself does not address the parameter, which is acceptable since the schema carries all necessary semantic information.

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 as 'legislation and regulation databases in the CanLII collection,' which distinguishes it from sibling tools like 'list_legislation' and 'list_case_databases.' It unmistakably conveys the tool's function.

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?

While it lacks explicit references to alternatives or exclusions, the description clearly implies usage when one needs to enumerate legislation/regulation databases, making the context of use transparent. No specific 'when not to use' is stated, but the tool's name and description draw a clear boundary.

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