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

With no annotations supplied, the description carries the full burden and does a solid job: it discloses the analysis method ('análisis estático por patrones de texto (no ejecuta el código)'), the auth requirement and credit model, and the concrete failure mode (responses mixed between clients). It does not describe what a finding looks like, severity scoring, or false-positive behavior, which is the main remaining gap for a scanner with no output 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?

Content is front-loaded and largely earns its place — the CVE/OWASP mapping and the non-execution caveat are genuinely useful. However, the core content is delivered as a single ~130-word sentence with nested em-dash clauses and two numbered sub-clauses, which is hard to parse; breaking the two detection patterns into separate sentences would improve scanability without adding length.

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 static analyzer with no annotations and no output schema, the definition covers input scope, detection logic, method, and auth. It leaves an important gap: nothing tells the agent what comes back (findings list, line references, risk verdict), so the agent cannot anticipate or interpret the result. Adequate but not complete for the tool's complexity.

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% and both parameters are already documented in the schema, including the note that 'lenguaje' is informational only. The description adds scoping meaning by specifying that 'codigo' must be the HTTP/SSE transport code rather than arbitrary source, but gives no format or size guidance beyond that, so the 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?

The description states a precise verb and resource ('Analiza el código fuente que arma el transporte HTTP/SSE de un servidor MCP') and then enumerates the two exact anti-patterns it detects: a module-level McpServer/Server instance reused across per-request transports, and a module-level mutable variable written in a request handler and read in a tool callback. It also anchors the check to CVE-2026-25536 and the OWASP MCP Top 10 entry, so an agent can distinguish this from the ~20 sibling detect_* tools without opening the 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?

Usage context is clear: feed it the HTTP/SSE transport source of an MCP server, and it is the same style of static detector as detect_dns_rebinding_risk and detect_missing_auth_risk, which tells the agent these are parallel, non-overlapping risk checks. It also states the prerequisite of a valid API key (free uses or credits, POST /crear-llave). It stops short of explicit exclusions, e.g. that it does not cover stdio transports or runtime behavior.

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