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

With no annotations, the description carries the full burden and does well: it discloses the number of checks, the finding shape (success criterion, offending markup, corrected example), and the analytical limits. It doesn't mention size limits or runtime cost, but nothing material is misleading.

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 sentences, front-loaded with purpose and followed by the capability boundary. The long rule enumeration is dense but each item earns its place by defining coverage.

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 correctly explains what comes back and in what form, which is the key missing piece. Only minor operational details (input size, latency) are absent.

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 both html and the severity_floor enum are fully documented in the schema. The description adds only the 'snippet or full page' nuance and never mentions severity_floor, 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 and resource (run 18 static WCAG 2.2 checks against HTML) and enumerates the covered rules, which makes it unmistakable against lookup_wcag_criterion or get_verified_fix_example. The scope ('snippet or full page') is explicit.

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 'Static analysis only' sentence defines clear exclusions (contrast, keyboard traps, focus visibility, reading order), which tells an agent when this tool will not answer the question. It stops short of naming siblings such as lookup_wcag_criterion as the alternative for explanatory lookups.

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 no annotations, the description carries the full burden and does reasonably well: it discloses the return shape (binding-now vs. upcoming items, days remaining, a primary source URL per date) and the temporal scope (1990 statute through 2027/2028 rules). It omits whether results are cached/static, whether 'as_of' shifts the binding classification, and any caveat about not being legal advice — meaningful gaps for a compliance-reference tool.

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 purpose and output contents are front-loaded, then the entity-type list closes it out. Slightly dense in the middle ('what is binding now, what is upcoming within the horizon with days remaining, and the primary source URL for every date'), but every clause conveys useful information and 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?

There is no output schema, so the description must describe return values — and it does, including the binding/upcoming split and source URLs. Remaining gaps are modest: the default and maximum for horizon_years, and what an 'unknown' entity_type yields, are not addressed anywhere.

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 67%, and the description compensates by enumerating seven of the eight entity_type enum values (omitting 'unknown', which is a real gap since that value's behavior is undocumented) and by implying horizon_years is a look-ahead window over which 'upcoming' items are reported. The as_of parameter's default is already covered by 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 ('return the dated web accessibility obligations that apply to an entity type') and scopes it to named legal sources and date ranges. This is clearly distinct from the sibling tools (audit_html_snippet, lookup_wcag_criterion, get_verified_fix_example), which cover code-level WCAG work rather than regulatory timelines.

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 clear: this is the tool for regulatory deadline questions, and the enumerated entity types show exactly when it applies. However, it never states when *not* to use it (e.g., for general WCAG conformance questions use lookup_wcag_criterion), so the routing is implied rather than 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?

No annotations are provided, so the description carries the full burden, and it does disclose real behavioral traits: every pair was executed in headless Chromium against axe-core 4.14.0, and the detection method is reported so the agent knows whether automation or manual review catches the defect. What it omits is what happens on no match and whether the response is paginated or ranked.

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 what is returned, then provenance/verification, then lookup modes. Each sentence carries distinct information an agent needs, and nothing is repeated.

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 annotations and no output schema, the description does the heavy lifting by enumerating the return payload (failing snippet, corrected version, AT impact, manual test step, detection method). It falls short only on the limit parameter and on match-failure behavior, which for a lookup tool is a minor 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?

Schema coverage is 67%. The description adds valuable format examples for sc_id (2.4.7) and pair id (wcag-1-4-3-01) and a keyword example (focus indicator), which go beyond the bare schema strings. However, it never mentions the limit parameter, never says whether query and sc_id can be combined or are mutually exclusive, and gives no default for the zero-required-parameter case.

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 concrete verb and resource: return a failing HTML snippet plus its corrected version for a WCAG 2.2 defect, along with an AT rationale and a manual test step. That is far more specific than the sibling tools, but it never names them, so an agent must infer on its own that lookup_wcag_criterion is for criterion text and this tool is for fix examples.

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 how to address a record (criterion number, pair id, or keyword) but never says when to reach for this tool instead of lookup_wcag_criterion or audit_html_snippet. The usage is implied by the content rather than stated as a routing rule, and no when-not guidance is given.

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 no annotations and no output schema, the description does real work: it enumerates the returned fields (level, principle, guideline, ADA Title II applicability, practical test, axe-core rules, W3C and Understanding links) and 'Search' implies a read-only operation. It omits pagination/limit behavior and result-count semantics, which are the remaining behavioral gaps.

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 dense sentences, each earning its place: the first covers input modes, the second covers output. Nothing is repeated from the schema and the search capability 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 read-only lookup tool with no annotations and no output schema, the description covers inputs and return contents well enough to call it correctly. The only shortfall is unexplained behavior for the limit and level 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 coverage is 33%: only 'query' is documented in the schema, and the description usefully extends it with axe-core rule names and concrete examples. However, the 'level' enum and especially the 'limit' parameter (caps results at 20) receive no explanation in either place, so the description only partly compensates for the coverage 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 (search) and a precisely scoped resource (the 87 WCAG 2.2 success criteria), plus the exact matching modes: number, name, keyword, axe-core rule. Siblings like audit_html_snippet and get_verified_fix_example are clearly different operations, so no disambiguation is needed.

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 lookup modes imply when the tool is useful, but there is no explicit statement of when to use it versus siblings (e.g., before auditing a snippet, or to resolve a rule id found by audit_html_snippet) and no exclusions. Usage is inferable rather than stated.

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