Docket Nexus

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

Annotations already establish readOnlyHint, idempotentHint, and non-destructive behavior. The description adds useful context: only public cases are accessible, results mirror the case page, and disposition appears only when recorded. This goes beyond the annotations without contradicting 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?

The description is one dense sentence with the action and identifier format front-loaded, followed by a precise field list. Every clause adds useful information; there is no 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?

With one required parameter, no nested objects, and safety fully covered by annotations, this description is nearly complete. It lists the return content despite the absence of an output schema. Only edge-case handling and explicit failure behavior are omitted, which is a minor gap for a read-only resource.

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 0%, so the description carries the full burden. It supplies a canonical URL template and indicates the parameter is the case identifier. The description does not cover invalid or not-found URLs, but it gives enough semantic grounding for correct invocation.

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 and resource ('Get a public case') and identifies the exact input form (Docket Nexus URL). It enumerates the returned fields, which clearly differentiates it from sibling tools like get_case_docket, get_document, and search_cases.

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 URL and 'public case' wording imply when this tool is appropriate, but the description never explicitly contrasts it with siblings such as get_case_docket or states when not to use it. The usage context is clear enough to guess, but not explicit enough to reliably route an agent.

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 safety profile is covered. The description adds valuable behavioral details: entries the site does not publish are omitted and only counted, and pagination is capped at 50 per call. This goes beyond the 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?

Three sentences, each carrying distinct information: ordering, pagination, and omission behavior. 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 read-only list tool with no output schema, the description covers ordering, pagination, limits, and omission behavior. It doesn't describe the return shape, but without an output schema that might be a gap; however, the core invocation details are present.

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 0%, so the description must compensate. It explains the cursor parameter's role in pagination and the limit's cap, but it doesn't explain the case_url parameter format or how limit interacts with the 50-per-call cap. The description adds some meaning but leaves gaps.

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 lists a public case's docket entries, ordered newest first, and includes document availability. It distinguishes itself from siblings like get_case and get_document by focusing on docket entries.

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?

It explains pagination with next_cursor and the 50-per-call limit, giving clear usage context. It doesn't explicitly say when to use this over alternatives, but the resource and action are specific enough that an agent can infer the right context.

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 non-destructive behavior. The description adds useful conditional nuance by noting verified identity appears only 'when on the verified roster' and clarifies the aggregate nature of the response, such as 'number of linked cases' and 'top case types and courts.'

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 filler: it states the verb, resource, key constraint, example, and output fields in order. The enumeration is dense, but every item earns its place and there is nothing irrelevant.

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 getter with no output schema, the description covers the input format and the main return contents, including the verification conditional. It does not describe error or unknown-slug behavior, but that is a minor gap for such a simple read-only tool.

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 0% and the single parameter is documented only by its title, so the description carries the burden. It explains that the slug identifies a company and gives a concrete example ('acme-widgets-inc'), making the expected value actionable despite the sparse 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 names a specific verb ('Get'), a distinct resource ('Docket Nexus profile'), an addressing mode ('by slug'), and enumerates returned fields, so an agent can tell this from get_case and search_cases. It does not explicitly contrast with get_company_cases, but the profile-vs-cases distinction is clear enough from the resource wording.

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 the agent has a company slug and needs an aggregate profile rather than case-level records. It gives no explicit when-not-to-use or alternative routing, such as pointing to get_company_cases for the full case list, so usage context 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 mark the tool as read-only, idempotent, and non-destructive, so the bar is lower. The description adds concrete behavioral details: ordering by newest/oldest, filtering by suit/court, next_cursor pagination, and a 25-per-call cap. 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?

Three short sentences with the main purpose first, then filters, then pagination and limit. Every sentence adds useful information with no filler or 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 list endpoint with no output schema, the description covers selection criteria, ordering, pagination, and result cap. It doesn't describe the case object fields or accepted sort/filter values, but those are not essential for deciding whether and how to call it.

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 0%, so the description carries the burden. It clarifies sort (newest/oldest), filters (court, nature_of_suit), and pagination (cursor, limit cap of 25). The required 'slug' is inferable from the tool name, though exact accepted values and defaults are not fully specified.

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 names a clear action ('List'), target ('public cases linked to a company'), and optional ordering/filters. The company-scoped public-case scope distinguishes it from get_case and search_cases, though it doesn't explicitly name the 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?

Usage context is implied: use this when you need a company's linked public cases, and pagination behavior is stated. However, it doesn't explicitly say when not to use it or contrast it with sibling tools like search_cases or get_case.

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 readOnly, idempotent, and non-destructive hints, so the safety profile is covered. The description adds 'public metadata' and 'Metadata only; no document text,' which is valuable context about the tool's return type and limitations. It doesn't contradict annotations and adds meaningful behavioral detail beyond what annotations encode.

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 concise sentences: the first states the action and the exact metadata fields returned; the second explicitly excludes document text. Every word contributes, and the core purpose is front-loaded.

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-id metadata lookup with no output schema, the description is complete. It lists the returned fields, clarifies the parameter source, and sets the expectation of 'metadata only,' so an agent can invoke the tool without needing additional context.

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?

With 0% schema description coverage, the description must compensate, and it does for the only parameter: 'by its Docket Nexus document id' clarifies what document_id means and its domain. It doesn't explain how to obtain that id, but for a single well-named integer parameter, this is sufficient semantic support.

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'), a specific resource ('public metadata for a docket document'), and an explicit field list (entry, date, description, page count, availability, parent case). It also adds 'Metadata only; no document text,' which clearly distinguishes this tool from any document-text retrieval and from sibling case/company tools.

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 clearly implies when to use this tool: when you have a Docket Nexus document id and need that document's metadata. It doesn't explicitly name alternatives or exclusions (e.g., 'use get_case_docket for the full docket'), but the focus on a single document by id is enough for an agent to select it correctly in most cases.

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?

Beyond the readOnly/idempotent annotations, the description discloses concrete behavior: results are newest first, capped at 25 per call, and pagination uses next_cursor. This is useful operational context that the annotations do not provide, though it stops short of describing errors or the exact return envelope.

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 tightly written sentences deliver the core query semantics, a concrete example, ordering behavior, and pagination guidance. No filler or redundancy; the most important information is front-loaded.

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 three-parameter read-only search tool, the description covers the essential usage: what to search, how results are ordered, the per-call cap, and how to paginate. Minor gaps include explicit limit semantics and alternative-tool routing, but nothing critical prevents an agent from calling it 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?

With 0% schema description coverage, the description carries the burden of explaining the query parameter, and it does so thoroughly with examples and a docket-number format caveat. It also implies the cursor parameter via 'paginate with next_cursor,' but the limit parameter is only indirectly addressed by 'at most 25 per call.'

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 ('Search'), a clear resource ('public cases'), and defines the accepted input forms (caption words, 'A v. B', or a federal docket number with office prefix). It is clearly distinguishable from sibling get_* tools, which retrieve specific records rather than performing searches.

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 makes it clear this is the search entry point for public cases and specifies what query formats are valid. It does not explicitly name alternatives or say when not to use it, but the search-vs-fetch distinction is strongly implied by the wording and sibling names.

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