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

With no annotations, the description carries the full burden and does so well: it discloses that matching is deterministic and rule-pack-driven rather than LLM-based, that findings carry a rule id and rationale and are reproducible, and it explicitly addresses false-positive behavior ('secure' is not flagged as 'cure'). This goes well beyond the schema.

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, all front-loaded on the core purpose with escalating detail about detection scope and matching strategy. Dense but largely waste-free; the matching example sentence is long yet directly justifies the tool's reliability claim, so it 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?

No output schema exists, and the description compensates by explaining the shape of findings (rule id plus rationale) and the severity model implied by failOn. Enough is present for an agent to call the tool and interpret results, though the exact finding payload structure is left implicit.

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 schema already documents all seven parameters including the platform rule-pack details and aiDisclosure semantics. The description adds the conceptual rule-pack framing but no parameter-specific syntax or edge-case guidance beyond what the schema provides, so the 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?

The description names a specific verb (audit) applied to a specific resource (cross-border e-commerce product listing) and enumerates the exact violation classes detected. It is immediately distinguishable from siblings like search_rules and suggest_rewrite, which serve different phases of the 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 clearly states the timing context ('BEFORE it gets flagged or removed by the platform'), which tells an agent when this tool belongs in a workflow. However, it never names an alternative tool or a when-not-to-use condition, so routing versus list_rule_packs/search_rules is left to inference.

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 behavioral burden. 'List the available' strongly implies a read-only discovery call, but the description never states there are no side effects, whether it paginates, or an auth requirement, leaving real gaps for an unannotated 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?

Two tight sentences: the first defines the operation and its return fields, the second gives the actionable next step. Nothing is redundant and the purpose leads the text.

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 usefully enumerates the returned fields, which compensates well. For a simple zero-param list tool the coverage is nearly complete, though it could note the read-only nature to fully stand in for the missing annotations.

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 per the baseline this scores 4. There is nothing for the description to disambiguate at the parameter level, and it commits no errors here.

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 ('List the available compliance rule packs') and enumerates exactly what each entry exposes (platform, market, version, update date, rule count). This lets an agent distinguish it from siblings like search_rules or suggest_rewrite without inspecting schemas.

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 tells the agent when to use it ('to discover which platforms are supported') and names the follow-up call (audit_listing), routing the agent correctly. It lacks explicit when-not guidance or mention of the other siblings, so it stops just 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?

With no annotations, the description carries the full behavioral burden. It discloses the return shape (id, severity, category, patterns, rationale, fix suggestion) and implies a read-only lookup, but says nothing about authentication, pagination, result limits, or whether the search is substring/regex based.

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 tight sentences: purpose, return contents, then motivating use cases. The essential verb+resource is front-loaded and no sentence is redundant.

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, but the description compensates by listing the returned fields, and all three parameters are fully documented in the schema. Minor gaps around result limits and query matching semantics keep 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%, so query, platform and severity are already fully documented including enum values and defaults. The description adds a natural-language example that subtly clarifies the query parameter's intent but no syntax beyond the schema. 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 ('Search inside a rule pack by keyword') and enumerates the returned fields, so the agent knows exactly what the tool produces. It does not explicitly contrast itself with siblings like list_rule_packs or suggest_rewrite, 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?

Gives concrete usage contexts ('why was this flagged?', 'what words are banned for supplements on Temu?') that tell the agent when this tool is the right call. It stops short of naming alternatives or exclusions, so no 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?

With no annotations, the description carries the full burden and does disclose meaningful behavior: output is grouped by field for direct patching, and suggestions are deterministic from the rule pack with the strong guarantee that it "never invents copy." It does not cover permissions, rate limits, or what happens when optional fields are omitted, so it is not exhaustive.

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 tight sentences, front-loaded with the core purpose, then the return shape, then the determinism guarantee. Every sentence adds distinct information with no repetition of the title or 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?

There is no output schema, so the description must describe returns, and it does (fragment, violation reason, replacement, field grouping). Combined with the determinism guarantee and full schema coverage on inputs, an agent has everything needed to call and interpret this tool.

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 aiDisclosure enum semantics, required platform, and optional copy fields are all fully documented in the schema. The description's only added detail is that results are "grouped by field," which describes output shape rather than input semantics, so it stays at the baseline for a fully documented 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?

Specific verb+resource (turn audit findings into rewrite guidance) with the output contract spelled out: offending fragment, policy rationale, and suggested replacement grouped by field. It implicitly distinguishes itself from audit_listing (which produces the findings) and the rule-pack siblings (which supply rules), so an agent can place it in the workflow 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?

The phrase "Turn audit findings into concrete rewrite guidance" clearly establishes the upstream dependency (it consumes audit output) and the intent to patch listing copy. However, it names no exclusion conditions and does not explicitly say when to prefer it over re-running audit_listing or browsing rules.

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