FAI Legal Research

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine value beyond that: the template is 'reviewed', and it discloses the return content and the anti-hallucination constraint on missing facts.

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 compact sentences, no filler, and the deliverable is front-loaded before the workflow instruction. Every clause 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?

Purpose, returned content, parameter source, and the operating constraint (ask, don't invent) are all present, and an output schema exists so return-value documentation is unnecessary. An agent has everything needed to invoke this 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?

There is a single parameter with 100% schema description coverage; the schema already documents template_id, its length bounds, and that it comes from list_drafting_templates. The description adds no additional parameter meaning, 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?

States a specific verb and resource ('Return one reviewed template') and enumerates the payload ('its structure, the facts that must be collected first, and the standard wording for its Pakistani forum'). The singular 'one' implicitly separates it from the sibling list_drafting_templates, which returns many.

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 clear operational context: ask the user for missing facts, never invent them, then fill the template. It also implies the template_id originates from list_drafting_templates via the schema. However, it never states when to prefer this tool over siblings like get_statute_section or search_judgments, and offers no exclusions.

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, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds only the retrieval granularity (one section, full text) and no auth, rate-limit, or not-found behavior, which is acceptable but modest given an output schema is also present.

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?

A single front-loaded sentence that states the action, the scope, and the triggering condition, then illustrates with two concrete pairs. No filler and nothing buried.

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 two-parameter lookup with an output schema and full annotation coverage, the description supplies everything needed to invoke it correctly. Minor gaps (behavior when a section is not found, exact identifier normalization) are tolerable given the output schema exists.

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% and both parameters already document accepted formats and examples ('PPC', 'CrPC', '489-F'). The examples in the description ('PPC'/'392', 'Constitution'/'199') largely restate the schema, 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?

States a specific verb (return) and resource (full text of one section/article of a Pakistani law) with concrete examples of the act/section pairings. The precondition 'when the act and number are known' implicitly separates it from search_statutes, which is the sibling an agent would otherwise confuse it with.

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 a clear precondition for use ('when the act and number are known'), which tells the agent to reach for a search tool when the citation is unknown. It does not name search_statutes as the alternative or state what happens on a miss, so it falls short of an explicit when/when-not rule.

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, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered. The description adds the 'reviewed' curation signal and the breadth of template categories, but says nothing about result ordering, count, or pagination behavior; with an output schema present, return-format detail is not required. Modest value added on top of 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?

Front-loaded with the verb and resource, and the workflow sentence is compact. The parenthetical category list is long-ish but earns its place by conveying the template breadth an agent needs to judge relevance.

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 annotations covering the safety profile, an output schema covering returns, and a fully documented single parameter, the description supplies the remaining essentials: scope, content breadth, and the chaining step to get_drafting_template. Only the absence of explicit non-use cases keeps it from a 5.

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% and the single filter parameter is fully documented in the schema with a default, maxLength and examples. The description adds nothing about filtering syntax or matching behavior, so 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?

States a specific verb (List) plus a precisely scoped resource (FAI's reviewed Pakistani legal drafting templates) and enumerates concrete examples (legal notice, plaint, bail application, affidavit, etc.). It also differentiates itself from the sibling get_drafting_template by positioning itself as the discovery step.

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 says to use it when the user wants to draft a Pakistani legal document, and gives the follow-up routing step (call get_drafting_template with the chosen id), which is a genuinely useful workflow hint. It does not state when-not to use it (e.g. use search_statutes or search_judgments for research rather than drafting), so it stops short of full alternative coverage.

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 readOnly, idempotent, non-destructive, closed-world behavior, so the description only needs to add semantics beyond that. It does: results are relevance-ranked, off-topic matches are dropped, and an empty list means no on-point judgment exists — all genuinely useful behavioral context not in 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?

Front-loaded with the core purpose, then scope, then usage examples and return shape. The enumeration of courts and multiple example queries is slightly verbose but each element earns its place by constraining scope or illustrating query style.

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 an output schema present and rich annotations, the description needn't explain return values — yet it usefully signals citation, court, judges, and relevance ranking plus the empty-result meaning. Complete enough for correct invocation, with only marginal gaps like the effect of combining court with year filters.

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%, including the court enum, limit max of 5, and year bounds, so the schema does the heavy lifting. The description reinforces query phrasing with example searches but adds nothing about the court filter, limit, or year range beyond what the schema already documents.

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 (find reported judgments / case law / precedents) and scopes it to named Pakistani courts, which cleanly separates it from the sibling search_statutes. An agent can tell immediately this is case-law retrieval, not statute lookup.

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 concrete trigger examples ("Supreme Court judgment on bike snatching", "precedent on specific performance") and states the jurisdiction boundary ("Pakistan only"). It does not explicitly name search_statutes as the alternative for statutory text, so the routing guidance is strong but not complete.

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 readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds real behavioral value beyond them: natural-language synonym matching ('murder finds qatl-i-amd, s.302 PPC') and the fact that section text plus citation is returned.

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 then scope then examples; every clause carries information. The act enumeration and example list are dense but justified for a multi-corpus legal search, though slightly long.

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 an output schema present, the description needn't explain returns, yet briefly notes section text with citation. Coverage of corpus, query semantics and scoping is sufficient for correct invocation; only explicit sibling routing 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 67% (limit is undocumented in the schema). The description compensates for the important parameter by explaining that query accepts everyday words, topics, or section references, and that act scopes the search to one statute, adding semantic detail the schema alone does not convey.

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+resource ('Find the sections of Pakistani laws relevant to a question') and enumerates the exact corpus covered (PPC, CrPC, CPC, Constitution, etc.), so an agent knows precisely what this returns versus a general web search.

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 concrete trigger examples ('punishment for snatching a motorcycle', 'bail in a non-bailable offence') that make the intended use unambiguous, and clarifies it handles everyday phrasing. It stops short of naming when to prefer get_statute_section (citation lookup) or search_judgments (case law) instead.

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