Nalegalu MCP

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

Annotations already declare readOnlyHint=true and destructiveHint=false, signaling safe read operations. The description adds behavioral context by noting the lookup is deterministic and that users must have a trusted source for parameters. This goes beyond the annotations, though it stops short of explaining error handling or return edge cases.

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 compact and front-loaded, with the core purpose stated in the first sentence. Subsequent sentences add necessary detail about usage and parameters without any filler. Every line 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 tool's moderate complexity (3 params, output schema present) and read-only nature, the description fully covers purpose, usage, and all parameter semantics. It also explains relationships to sibling tools, addressing the context in which the tool should be invoked. The output schema handles return-value details.

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 zero description coverage, so the description must compensate—and it does thoroughly. It explains the address with an example (WDU19740240141), the article key with formats ('133' or 'Art. 133.'), and the optional paragraph key ('1' or '§ 1.'), including its narrowing purpose.

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 begins with a specific verb and resource: 'Fetch the exact text of one article (or paragraph) of a Polish legal act.' This clearly distinguishes it from sibling tools like search_law, which searches, or get_case, which fetches 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 description explicitly instructs when to use the tool: 'Use after search_law or another trusted source supplied the address and article key; never guess them.' This is direct usage guidance that also serves as a safety check, and it differentiates the tool from search_law.

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/openWorld/non-destructive, but the description goes further: long judgments are paged, responses may return ok=false with a fallback hint when SAOS is unavailable or rate-limited, and the correct recovery is an out-of-band fetch of saos_url. This is exactly the failure-mode and rate-limit context annotations cannot express.

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 one-line purpose, then the precondition, then paging, then the failure path — each sentence adds distinct operational value with 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?

An output schema exists, so return-value documentation is unnecessary; the description covers the invocation prerequisite, pagination loop, and degraded-mode behavior. An agent has everything needed to call 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?

Schema coverage is 0%, so the description must carry all three params. It clarifies offset semantics indirectly ('call again with offset=next_offset') and hints at max_chars via 'bounded text excerpt', but never defines saos_id's meaning and leaves max_chars' unit/default behavior to 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?

States a specific verb and resource ('Fetch one SAOS court judgment') plus the payload shape ('metadata + bounded text excerpt'). It is immediately distinguishable from siblings like related_cases, research_cases, and search_case_by_signature, which are named as ID sources rather than as 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?

Explicit precondition: 'Use only with a saos_id returned by related_cases, research_cases, or search_case_by_signature.' It also states the when-not case — do not retry on rate-limiting/unavailability, fetch saos_url instead — and gives the paging procedure with has_more/next_offset.

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, the description details important behavioral caveats: related-case links may not be textually confirmed, uncertain relevance should be discounted, and mentions=0 or missing context means the link is unverified. It also explains how results are ordered by relevance score, which is valuable runtime behavior not stated in 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 main purpose is first sentence. All subsequent sentences carry substantive caveats or detail about result interpretation, and the warning about not treating counts as exhaustive is placed where it will not be missed. It is watchfull but not padded.

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 covers about return fields, sorting, data provenance differences between richer and older data, how to interpret mention_match and mentions, and the local non-exhaustive boundary of the dataset. Given the output schema exists for return structure, the tool-level description leaves no meaningful calling or interpretation gap.

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 schema description coverage at 0%, the description compensates by explaining address and article_key with a concrete example (WDU19740240141) and by mentioning paragraph-level detail implicitly through 'one statutory provision.' It does not explicitly describe paragraph_key or limit, but limit is simple and paragraph_key is optional with a null default, so the important calling semantics are covered.

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-resource statement: 'List SAOS cases related to one statutory provision.' It further defines the lookup as deterministic by act address and article key, which clearly separates it from siblings like get_case or research_cases. The scope is precise and actionable.

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 says 'Use after identifying a relevant provision,' giving a clear precondition. It also warns against treating related-case links as proof and directs the agent to inspect the judgment with get_case before asserting holdings. It further clarifies that a zero count is not an exhaustive SAOS or case-law search, providing both when-to-use and when-not-to-conclude 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 cover the safety profile (readOnly, non-destructive, open-world), and the description adds real behavioral depth beyond them: the statute-then-provision-link search flow, deduplication by SAOS ID, the conditional dependency on server-side Cohere configuration, and the cap on fetched excerpts. That is meaningfully more than the annotations disclose.

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 layered caveats in an efficient order (pipeline, stage choice, reranker condition, follow-up). The embedded indentation and backtick formatting are artifacts of source docs but the prose itself is tight.

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?

An output schema exists so return values need not be described, and the pipeline/caveats are well covered. However, for a 9-parameter tool with 0% schema description coverage, six tuning knobs remain unexplained, leaving an agent without guidance on how to shape result size or cost.

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% across 9 parameters, so the description carries the full burden. It explains 'rerank' and 'rerank_fetch_limit' clearly, but leaves candidate_limit, provision_limit, context_max_chars, case_text_max_chars, cases_per_provision, and rerank_result_limit entirely undefined in both places.

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 ('Discover related-case candidates') plus the input type (natural-language legal issue), and sketches the internal pipeline. It does not, however, distinguish itself from the sibling tool 'related_cases', which an agent could easily 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 explicit stage selection guidance (rerank=false is the inexpensive discovery stage; rerank=true reranks only when a Cohere reranker is configured) and a clear follow-up directive to call get_case for every judgment used. No explicit when-not-to-use rule against 'related_cases' or 'search_case_by_signature', so it stops short of 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?

Goes well beyond the readOnly/openWorld annotations: discloses the local-index-first-then-live-SAXS lookup order, the exact verdict semantics (confirmed/not_found/outside_coverage/unverified) with interpretation guidance, the warning that courts reuse signatures, and the has_text implication for verify_quote.

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 and the example, and every block of text carries actionable content. It is dense and slightly list-like, 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?

An output schema exists, yet the description still pre-empts the most decision-critical return field (verdict), which is exactly what an agent needs to interpret results and route to alternatives like CBOSA or verify_quote.

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%, so the description must compensate; it supplies an example signature format and enumerates the court_type values (COMMON, SUPREME, CONSTITUTIONAL_TRIBUNAL, NATIONAL_APPEAL_CHAMBER) that the schema only types as a bare string. The 'limit' parameter remains unexplained, so it is not fully compensating.

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 ('Verify a cited case signature') with a concrete example, and its verification role is clearly distinct from siblings like get_case, research_cases, and verify_quote.

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 when to use it ('before relying on a judgment cited by a user or another agent') and gives a when-not/alternative route ('administrative courts NSA/WSA are not in SAOS — verify in CBOSA instead').

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 annotations (readOnlyHint=true, destructiveHint=false), the description adds useful context: 'Results are primary-source material, not legal advice' and 'current Polish statutes,' clarifying scope and limitations. It does not describe pagination or rate limits, but the annotations cover safety traits.

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 compact and front-loaded. Each sentence earns its place: purpose, when to use, example, filter guidance, and disclaimer. No redundant 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 12 parameters and no schema descriptions, the description covers the common path well but leaves many tuning parameters unexplained. The output schema exists, so return structure is available, but the description alone is not enough to fully understand all 12 parameters.

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 query parameter with a Polish example and clarifies when not to use the filter parameters (address, domain, etc.). However, advanced parameters like retrieval_mode, case_law_boost, and candidate_multiplier remain undocumented, leaving 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 opens with 'Search current Polish statutes and return article-level hits,' which uses a specific verb, resource, and output granularity. This clearly distinguishes it from sibling tools like get_article, get_case, and search_case_by_signature, which target specific documents or case 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?

It explicitly says 'Start here' for natural-language issues or direct citations, and instructs not to add domain, address, article, act_type, or status filters unless the user provided them. This gives strong when/when-not guidance, though it does not name alternative tools explicitly, keeping it from 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 cover the safety profile (readOnly, non-destructive, openWorld), and the description goes well beyond them: it enumerates the three verdict states with their meanings, explains the normalization rules behind 'exact', and instructs what to do on ok=false with a fallback hint. This is unusually 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?

Front-loaded with the core purpose, then prerequisites, then verdict semantics, then fallback behavior — a sensible order with no filler. It is a little dense across five sentences for a three-parameter tool, but every clause conveys actionable 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?

An output schema exists, so return structure need not be documented, yet the description still explains the verdict vocabulary and the ok/fallback-hint protocol. Combined with the prerequisite and normalization notes, an agent has everything needed to call it correctly and interpret the result.

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%, so the description carries the burden. It documents saos_id (integer id sourced from search_case_by_signature or related_cases), quote formatting ('as quoted', with whitespace/quote-mark/dash normalization), and implies the similarity score that min_similarity controls. min_similarity itself is never named or explained, which is the one gap.

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: 'Check whether a supplied quote appears in a SAOS judgment.' It also articulates scope precisely — 'validates wording, not whether the quote supports a legal conclusion' — which distinguishes it from research/argument-oriented siblings. An agent can tell it apart from get_case or search_case_by_signature without opening any schema.

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 an explicit precondition ('Use only after resolving the judgment to a saos_id'), names where the saos_id comes from (search_case_by_signature or related_cases), and states what the tool is not for. It also handles the failure path: retry versus falling back to saos_url with the agent's own web tools.

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