Workers' Rights

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

Annotations already indicate a safe, read-only, non-destructive operation, and the description adds meaningful behavioral context beyond that: it is educational information rather than legal advice, and it discloses a critical exception for federal employees with a 45-day EEO counselor deadline. This gives the agent important limitations and caveats that annotations alone cannot convey.

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 moderately long but front-loaded with the core purpose and return value before the usage caveats and disclaimer. Every sentence earns its place given the legal complexity; it could be slightly tighter, but 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 no output schema, the description takes on the burden of explaining what the tool returns, which it does thoroughly: statutes, citations, employer-size thresholds, filing deadlines, agencies, and remedies. It also covers parameter-specific exceptions and the educational nature of the output, making it complete enough for an agent 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 the baseline is 3, but the description adds value by showing how parameters interact: state is only relevant when provided, and employer_sector maps to the federal-employee exception with a separate deadline. It also gives concrete examples for issue and protected_class that reinforce the 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 uses a specific verb and resource: explaining applicable employment-law rights based on issue and/or protected class. It clearly distinguishes this tool from procedural or attorney-search siblings by specifying that it returns statutes, citations, coverage thresholds, deadlines, agencies, and remedies.

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 tells the agent to use this tool to ground an answer about a worker's legal protections, giving clear context for when it applies. It does not name alternatives or state when not to use it, so it falls just short of full routing 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?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses data provenance (public-source), result attribution, sorting, and important limitations: person-specific filters only apply when the directory supports them, and Google Places metrics are never presented as individual attorney ratings. This is substantive behavioral context that protects against misuse.

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: the first states the exact purpose and scope, the second summarizes return data and ordering, the third states caveats. Every sentence carries distinct, non-redundant information, 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?

The description provides enough about return content and limitations for a tool with no output schema, and the schema richly documents all parameters, including required-state semantics. Minor gap: it doesn't restate the state-or-lat/lng requirement, but that is fully covered by schema descriptions, so it doesn't materially hurt 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 the baseline is 3. The description adds cross-cutting meaning that isn't in any single parameter: person-specific filters apply only where the underlying directory supports them, and Google Places metrics are labeled as firm/office data, never individual ratings. This helps the agent reason about filter behavior globally.

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 ('Find'), a specific resource ('public-source employment-law attorney listings'), and scope ('near a US location'). It also lists return fields (source-attributed identity, firm, location, contact data) and sorting, clearly distinguishing this from general legal-research or track-record siblings.

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 description (finding attorneys near a location), and the caveat that listings are not state-bar verification or an endorsement hints at non-uses. However, it does not explicitly say when to prefer this tool instead of siblings like get_attorney_track_record or explain_my_rights.

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 annotations covering the safety profile, the description still adds substantial behavioral context: counts at three levels with a detailed breakdown for one, thin-data behavior ('A level with few opinions returns counts without a win rate'), and precise semantics of wonPct, sentBack, wentForward and legacy compatibility. It also discloses the educational-use constraint and the non-prediction framing.

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 purpose and return summary, then caveats. It is dense and somewhat long, particularly the final structured-stages sentence, but each clause carries semantics an agent needs; minimal waste.

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, and the description fully compensates by enumerating return fields, level semantics, thin-data behavior, and field-level definitions, plus the required caveats. An agent can call and interpret this correctly without further documentation.

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%, so the baseline is 3, but the description adds meaning beyond the schema: it explains the three count levels and that only one level drives the detailed breakdown/examples, and clarifies the narrow_to_laws scope ('every opinion sharing the claim type, under any law'). This goes past restating field docs.

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 (analyze how similar cases were decided) plus the exact outputs (win rate, settlement rate, damages range, topics, representative cases). It clearly differentiates from siblings like search_rulings and get_employer_track_record by framing itself as an aggregate statistics tool over published opinions.

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 implied by 'Given the facts of an employment situation — claim types, protected class, employer, state' and the required output framing, but there is no explicit when-to-use/when-not or routing to alternatives such as search_rulings or get_employer_track_record. The extensive caveats are about interpretation, not tool selection.

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/openWorld/destructive annotations, the description discloses that data comes from federal court dockets, that facts are returned as-is, that attorney identity matching is algorithmic, that ambiguous/low-confidence matches are excluded, and that duplicate source rows are normalized. This gives an agent a reliable mental model of the tool's 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 information-dense without filler, opening with the core purpose and then adding usage context, data sourcing, matching caveats, and deduplication semantics. Every sentence earns its place and supports correct tool selection or invocation.

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?

There is no output schema, so the description appropriately enumerates the returned fields: case caption, court, year, nature-of-suit, and the side the attorney appeared for. Combined with annotation coverage, schema documentation, and dedup details, the tool is fully described for correct invocation.

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 the schema already fully documents both parameters. The description adds context about attorney matching quality and case deduplication but does not materially extend the meaning of the 'attorney' or 'limit' parameters beyond what the schema provides.

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 the exact verb (return), the resource (federal employment-law cases on file), and the subject (an employment attorney by name or slug). It enumerates the returned fields, making the tool's scope concrete and clearly distinct from the sibling get_employer_track_record.

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 states when to use it: 'Use this when a user names an attorney and wants their public litigation history.' It does not explicitly list exclusions or mention the employer-focused sibling, but the 'employment attorney' framing and sibling names make the boundary reasonably clear.

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/openWorldHint/destructiveHint=false, so safety is covered. The description adds real value beyond that by stating the data is 'live' and that it reflects the 'date the corpus was last updated' and outcome distribution before filtering, which tells the agent this is a point-in-time snapshot, not cached or filterable output.

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 verb and resource, then lists the returned metrics compactly, and closes with the intended use. The metric enumeration is dense but every item earns its place given there is no output schema.

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 takes on the burden of describing the return payload and does so completely (record counts, attorney listings, source count, last-updated date, outcome distribution). An agent knows what it will get and when 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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no input is needed and instead spends its words describing the output surface.

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 (return) and resource (live statistics about the Workers' Rights corpus) and enumerates exactly which figures are returned. No sibling tool overlaps with a stats endpoint, so it is trivially distinguishable.

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 use cases: 'establish scale/credibility' or answer 'how much data do you have / how current is it'. It gives clear positive context, though it names no alternatives or when-not conditions — reasonable here since no sibling covers this function.

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 only mark the tool read-only/open-world; the description goes well beyond by explaining that calls return either a stage overview with typical durations or a stage deep-dive with tips and do/don'ts. It also discloses the coverage boundary (private-sector/state/local) and the separate federal EEO process, so an agent won't misuse it for federal employees.

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 sentences each carry distinct information: what the tool is, how to invoke it for overview vs deep-dive, when to use it, and its scope/exclusion. Information is front-loaded and there is no fluff or repetition of the 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?

For a single-optional-parameter informational tool with no output schema, this description is complete: it covers invocation modes, return content, use triggers, and a key scope exclusion. Nothing an agent needs to decide whether to call it or how to call 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?

The schema already fully documents the optional stage parameter and the omit-for-overview behavior, so the description adds little new parameter syntax. It does enrich the mental model by describing what a stage deep-dive returns, but baseline 3 is appropriate because the schema covers the actual parameter semantics.

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 resource ('EEOC discrimination/retaliation charge') and a clear action ('Plain-English guide to the 9 stages'), and immediately distinguishes the two invocation modes (overview vs stage deep-dive). This makes the tool's job unambiguous and distinct from the rights/attorney sibling 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?

'Use this whenever someone asks what happens after filing with the EEOC' gives explicit trigger conditions, and the federal-employee caveat tells the agent when this tool is not appropriate. While no sibling is named, the when-to-use and when-not-to-use guidance is sufficiently explicit.

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 readOnlyHint=true and destructiveHint=false, annotations already establish safety. The description adds useful behavioral context: it covers only federal cases and trusted published opinions, includes docket records without opinions, and distinguishes the example limit from the full-corpus totals. 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 concise and front-loaded with the core purpose, and the usage trigger is a single final sentence. It packs many output components into one long sentence, but there is no wasted wording 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?

Without an output schema, the description carries the burden of listing return values, and it does so thoroughly: cases, opinions, outcome breakdown, notable opinions, and docket counts. It also clarifies scope (federal, trusted, published) and when to call it, making the tool actionable for an agent.

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 the schema already documents employer and limit, including suffix-matching behavior and the limit range. The description reinforces that the tool takes an employer/company name, but does not add substantial new parameter-level meaning 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 names a specific verb (return) and resource (an employer's litigation track record), and enumerates the exact outputs: distinct federal cases, trusted published opinions, outcome breakdown, notable opinions, and docket count. The phrase 'when a user names their employer' clearly separates it from sibling tools like get_attorney_track_record.

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?

'Use this when a user names their employer and wants that company's litigation history + footprint' gives explicit invocation context. It does not name alternatives or state when not to use it, but the trigger condition is clear enough for 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 mark this read-only/non-destructive, so the description's job is to add context beyond that — and it does: it flags time-sensitivity, explains that employers often revoke access during the termination call, names the three priority tiers, and draws an explicit legal boundary (no copying/forwarding from employer systems). That is substantive operational guidance.

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 purpose and triggers, and the negative boundary earns its place. It is somewhat long and repeats the section definitions that also appear in the schema, which is mild redundancy, but no sentence is 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?

There is no output schema, yet the description tells the agent what the result will contain (sections 'today', 'this-week', 'quiet') and why timing matters. For a single-optional-parameter read tool, an agent has everything needed to select and call 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?

Schema coverage is 100% and the enum values are already documented, so the baseline is 3. The description goes slightly beyond by attaching priority meaning to each section ('today' = highest-leverage, minutes matter; 'quiet' = low-priority prep) and stating that omitting the parameter returns the full checklist, which aids 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?

States a concrete verb+resource (produce an evidence-preservation checklist) with the specific scope: what to write down, what records the worker already owns, and how to enumerate the rest for an attorney. It is clearly distinguishable from siblings like explain_my_rights, find_employment_attorney, or get_eeoc_process, which handle adjacent but different jobs.

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 explicit triggering conditions ('about to be fired', 'retaliation is escalating', 'mentions a PIP or sudden access changes', 'asks what to do before reporting discrimination') and an exclusion ('does not advise copying or forwarding material from an employer's systems'). This is close to a full when/when-not specification.

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 establish readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real value beyond that: it discloses the result shape ("published opinions with citations, outcomes, procedural stage, employers, claim types, recorded monetary amounts, and links") and a quality-filtering behavior ("low-confidence and junk rows excluded"). Missing pagination/rate-limit notes keeps it from 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?

Three sentences, front-loaded with scope, then return contents, then intended use. No filler, no repetition of the tool title, and each sentence adds a distinct fact.

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 9 optional filters of varying formats and no output schema, the description correctly compensates by summarizing the return fields and the quality filter. It could say more about default result count, paging, or what happens when no filter is supplied, but nothing essential for calling the tool 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 every parameter already carries a descriptive name plus examples (law ids, court ids, circuit display forms, date patterns), so the schema does the heavy lifting. The description only restates the filter axes at a high level and adds no syntax or interpretation beyond the schema, making the baseline 3 correct.

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 ("Search published employment-law rulings from our research corpus") and enumerates the filterable dimensions, so the agent knows exactly what this tool retrieves. It does not explicitly position itself against nearby siblings such as find_similar_cases or get_corpus_stats, which keeps it short of a 5.

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?

Provides a clear use context: "Use this to ground any claim about how employment cases have been decided." That tells the agent when the tool is appropriate, but there is no guidance on when not to use it or which sibling (e.g. find_similar_cases) to prefer for adjacent needs.

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