Ranuk Web Accessibility & AST Security Auditor

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

With no annotations, the description must carry the behavioral burden. It usefully enumerates the exact detection classes (secrets, eval/exec/shell=True), which is the core behavior of a static analyzer, but it never states that this is a read-only static analysis with no code execution, does not mention severity levels, false positives, or what the result looks like.

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?

One front-loaded sentence with zero filler and the detection scope up front. It is appropriately sized, though so terse that usage and output expectations are simply absent rather than economically expressed.

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 one-parameter static checker with no output schema, the agent still lacks the return format (findings list? severity? line numbers?), the supported language scope (eval/exec/shell=True implies Python only), and confirmation that the analysis does not execute the code. Enough to select the tool, not enough to interpret its output.

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, so the schema already documents 'code' fully, including the pre-commit/pre-merge intent. The description adds only that the input is source code, which is largely redundant with 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 ('Analiza') and resource ('código fuente') plus the exact detection targets: exposed secrets and insecure eval/exec/shell=True usage. An agent immediately knows what the tool does. It does not name or differentiate itself from the only sibling, wcag_quick_scan, but that sibling is an unrelated accessibility scanner, so confusion risk is low.

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 itself gives no when-to-use or when-not-to-use guidance and names no alternative. Usage context is only implied, and the actual trigger ('antes de commit o merge') lives in the parameter schema rather than the description, so an agent must infer that this is a pre-commit/pre-merge gate check.

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 present, the description carries the full burden. It does disclose that the scan is 'en vivo' (implying a live network fetch with latency and external dependency) and that output includes verifiable violations plus remediation links, but says nothing about scan depth limits, timeouts, rate limiting, or whether the call is purely read-only.

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 compact sentence that front-loads the action and the standards covered, with zero filler. It loses a point only because so much is packed in that nothing addresses scope or limits.

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 2-parameter, no-annotation, no-output-schema tool, naming the return payload is helpful, but the definition leaves gaps an agent would care about: how deep a 'quick' scan goes, whether the domain must be publicly reachable, and what the locale parameter changes.

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 only 50%: `domain` is documented in-schema but `locale` (enum en-US/es-ES/it-IT, default es-ES) has no described effect. The description adds nothing about parameters — notably it doesn't say that language controls the language of returned violations, which would be the key semantic an agent needs.

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: a live WCAG 2.1 AA / ADA / EN 301 549 scan of a domain, plus what it returns (verifiable violations and remediation links). The accessibility- vs security-audit distinction from the only sibling (ast_security_and_secret_audit) is inferable but never stated explicitly, and the description is in Spanish while the tool name is English.

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?

No indication of when to pick this over the sibling security auditor, no prerequisites (public reachability, auth, rate limits), and no explanation of what 'quick' excludes versus a full audit. The agent must infer all usage boundaries.

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