Lipe Court Record

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; the description adds useful behavioral context by listing what is returned: exact PDF page, reviewed evidence, provenance, permanent citation URL, and classification. It does not contradict the annotations and adds value beyond 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?

Two focused sentences with no filler: the first states the tool's purpose and the second gives an actionable instruction. The key 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 single-parameter fetch operation with an output schema present, the description covers what the tool retrieves and how to use the result. It is slightly thin on prerequisites or alternatives, but the low complexity and annotations keep 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?

The schema has a single undocumented 'id' parameter (0% coverage), so the description carries the burden. It conveys that the id refers to a specific search result, but it does not explicitly state where the id comes from or its expected format, leaving some ambiguity.

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 action (fetch), a specific resource (one search result's PDF page, evidence, provenance, and citation URL), and identifies the operation as retrieving a single item rather than listing or searching. This clearly distinguishes it from siblings like search and get_case_overview.

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 the tool is used after a search result is selected ('one search result's'), and tells the agent to use the returned classification and citation in the answer. However, it does not explicitly state when to prefer fetch over get_case_overview or list_case_topics, beyond the implication that fetch is for detailed evidence of a single result.

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, so the description's extra value is that it returns a concise, reviewed orientation and is not the tool for exhaustive detail. That clarifies scope and avoids over-reliance on it for follow-up questions. 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 no filler. The purpose is front-loaded, the usage guidance follows naturally, and the parameter explanation is compact. Every sentence contributes meaningful information.

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, read-only tool with one parameter, an output schema, and strong annotations, the description covers purpose, usage timing, workflow sequencing, and parameter provenance. Nothing essential is missing for an agent to select and invoke the tool 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?

Though the schema has no description for `case`, the description supplies the essential meaning: it is a case id obtained from list_cases. Since this is the only parameter, the description covers the critical semantic gap, though it does not clarify the meaning of the default/null or optionality.

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 ('Return'), the resource ('a concise, reviewed orientation to one case'), and specific contents (evidence classifications, page citations). It also distinguishes itself from sibling tools by framing the output as an orientation rather than detailed results, so an agent can tell it apart from search and fetch.

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 explicitly says when to use it ('Use for first-time users') and describes the sequence: 'then search and fetch before answering detailed questions.' It also tells the agent where the `case` parameter comes from ('a case id from list_cases'), giving clear routing guidance relative to siblings.

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 semantics, and the description adds substantial behavior beyond them: normalization of curly quotes, dashes, ligatures and line breaks; case-insensitivity by default; the warning that matches are extracted text rather than verified content; and the meaning of a zero-match result. This is exactly the extra context an agent needs before quoting a hit.

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-loads the core purpose in the first clause, then layers usage, filtering, normalization and caveats in order of importance. Sentences are dense but every one adds a distinct fact; nothing is restated from the schema or annotations.

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?

Even though an output schema exists, the description briefly outlines the return shape (total count, per-filing counts, page id, citation, snippet) and supplies the critical trust caveat that results are unverified extracted text. For a search-style tool with six parameters, nothing an agent needs to invoke it correctly 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?

With 0% schema description coverage the description must carry the load, and it explains `mode` (phrase/word/regex), `case_sensitive`, and `document` as a filename-substring filter. However, it never explains the `case` parameter, which is easily confused with `case_sensitive`, nor the `limit` parameter, leaving two of six parameters undocumented.

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 precise verb and resource ('Find every page whose extracted text contains...') and immediately scopes the mechanism to exact phrase, whole word, or regex. It is clearly distinguishable from the sibling `search`, which it explicitly characterizes as ranking by meaning.

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?

Names concrete use cases (quotation, dollar figure, cause or exhibit number, name, defined term) and names the alternative tool `search` along with the condition that selects it ('search ranks by meaning and may miss the exact words'). An agent can route between the two without opening either 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 provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered structurally. The description adds useful context about id reuse and the connector's case list, but it doesn't disclose ordering, pagination, or potential size/volume behavior. This is acceptable given the annotations, but not a rich behavioral disclosure.

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: the first leads with the action and output fields, the second gives actionable downstream routing. Every clause earns its place, with no repetition of schema or annotation information.

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 zero-parameter, read-only, idempotent tool with an output schema, the description covers the essential invocation and data-retrieval context. It also provides the crucial integration detail that page ids from search name their case. Nothing required to call the tool correctly appears to be 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?

This tool takes zero parameters and the schema is empty, so there are no parameter details to explain. The description sensibly avoids inventing parameters and instead clarifies that the returned id is the `case` parameter for sibling tools, which is helpful cross-tool semantics. Baseline 4 is appropriate for a zero-parameter tool.

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 exact resource ('court cases this connector holds'), while enumerating the returned fields (id, caption, cause number, court, status, incident). It also differentiates itself from sibling tools by explaining how its returned id feeds into search, get_case_overview, list_case_topics, and list_record_limitations.

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 establishes the context: call this tool to enumerate all cases held by the connector and obtain reusable ids. It explicitly documents how the id should be passed as the `case` parameter to sibling tools and notes that every page id from search names its case. It stops short of a full 5 because it doesn't explicitly state when not to use list_cases or directly contrast it with alternatives.

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. The description adds context about what content the tool surfaces, but it does not describe any additional behavioral traits such as pagination, limits, or behavior when no case is provided. 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 two sentences with no filler. The first sentence states the core behavior, and the second sentence gives both the usage trigger and the parameter origin. Every part 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?

Given the single optional parameter, strong annotations, and presence of an output schema, the description is nearly sufficient. The only notable gap is that it never states what happens when `case` is omitted, even though the schema marks it as nullable and not required.

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 carry the parameter meaning. It does so by explaining that `case` is a case id from list_cases, which is meaningful and actionable. It could further clarify the null/optional behavior implied by the schema, but it compensates well for the missing schema descriptions.

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 states a specific verb ('List'), a precise resource ('evidence topics covered for one case'), and the output concept ('suggested questions'). It clearly differentiates this tool from siblings like get_case_overview or search by naming the case-topic investigation angle.

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 explicitly says when to use it: 'when the user asks what the connector knows or what they should investigate.' It does not list exclusions or when a sibling would be better, but the trigger context is concrete and actionable.

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 description goes beyond the read-only, idempotent annotations by explaining the nature of the output—what the record does NOT establish and the kinds of limitations included. This enriches the agent's understanding of the tool's behavior without contradicting the provided 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 concise, front-loaded with the core purpose, followed by usage guidance, and finishes with a compact parameter pointer. Each sentence earns its place without wasting tokens.

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 and strong annotations plus an output schema, the description covers the core purpose and a typical invocation context. The main gap is the optional parameter's default behavior, which could still lead an agent to call it without a case and get unexpected results.

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 description adds a valuable pointer by noting that `case` is a case id from list_cases, which is necessary because the schema has no description for the parameter. However, the parameter is optional with a default of null per the schema, and the description does not clarify what happens if case is omitted or null, leaving a meaning gap for an agent selecting and invoking the tool.

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 that the tool lists the limitations of a case's reviewed record, including unavailable filings, unverified facts, review scope, and legal conclusions the record can or cannot support. This is a specific verb-object structure and usefully differentiates it from sibling tools that return positive case information, such as list_case_topics or get_case_overview.

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 explicit guidance on when to use the tool: before asserting the record establishes something, or when search results do not squarely answer a question. This is good context but it does not name alternative tools or explicitly state when not to use it, so a small part of the routing burden remains on the 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 the tool as readOnlyHint=true, openWorldHint=false, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by disclosing that each result includes a reviewed-evidence-ledger flag and a classification, and by instructing the agent to prefer reviewed pages. It also explains the `case` constraint behavior. These are meaningful beyond the annotations, though it does not discuss pagination or result limits, which would have made it 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 dense but every sentence earns its place. It front-loads the primary purpose, then gives usage sequencing, result-selection guidance, and the parameter constraint. There is no filler or repetition, and it remains readable despite carrying substantial operational detail.

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 complexity (a search across court records with a result-selection policy and an optional case filter) and the presence of an output schema (which presumably documents return fields), the description covers the critical aspects: when to call, how to follow up, how to interpret results, and when the case parameter is mandatory. It does not explicitly discuss error handling, pagination, or query syntax, but these are either inferred or covered by the output schema, making it adequate.

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% (the schema provides no property descriptions). The description explains the `case` parameter in detail: it confines the search to a specific case id from list_cases and becomes required when multiple cases are held. However, the required `query` parameter is only implied by the phrase 'Search... for case facts' and is never explicitly described (e.g., format, free-text vs. structured). This is partial compensation for a low-coverage schema, so a 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 opens with a specific verb and resource: 'Search the court record for case facts, testimony, positions, rulings, and jury findings.' This clearly defines what the tool does and implicitly differentiates it from siblings like fetch (which retrieves documents) and list_case_topics (which enumerates topics). The additional instruction to call fetch on result IDs further clarifies the search-then-fetch workflow.

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 explicitly states when to use the tool: 'Call this for every case-specific factual question' and provides the follow-up action: 'then call fetch on relevant result IDs before answering.' It also gives a conditional rule for the `case` parameter ('required once more than one case is held') and advises preferring reviewed pages over automatically extracted ones. This is direct, actionable guidance with no ambiguity.

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