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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses important behavioral traits: it is a composite call fanning out across two services, it may take 5-30s on first bundlephobia measurement, and partial failures degrade gracefully with a 'sources_failed' field. This explains latency, failure handling, and aggregation behavior, which directly affects how an agent interprets results.

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 information-dense yet well-structured: it opens with purpose, then usage triggers, return summary, ecosystem scope, and failure behavior. No sentence is redundant; every phrase adds value essential for invoking a composite tool without an output schema. Front-loading the main purpose makes it immediately scannable.

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 complexity (multi-source composite, no output schema) and rich annotations, the description fully compensates. It enumerates the summary block fields (is_latest, license, advisory_count, etc.), mentions per-advisory detail, links, alternative versions, and the graceful degradation mechanism. This is a complete picture for an agent to understand what the tool returns and how to handle partial results.

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 input schema already has 100% coverage, thoroughly describing both 'package' (npm package name, scoped packages accepted) and 'version' (specific version, default latest). The description does not add new parameter-level detail beyond what the schema provides; it reinforces the purpose but doesn't expand on syntax or edge cases. Meets the baseline for high schema coverage.

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 crystal-clear statement: 'Composite should I add this npm package to my project' check in ONE call.' This identifies the specific verb, resource, and scope, and distinguishes it from siblings by narrowing to npm only. It explicitly details the two data sources (deps.dev and bundlephobia) and the types of information gathered, leaving no ambiguity about the tool's purpose.

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 gives explicit usage triggers: 'Use whenever an agent asks "is X safe / popular / small" or "what does adding lodash cost me".' It also provides an exclusion and alternative: 'NPM ecosystem only in v1; PyPI / Maven / Cargo / Go fall under deps.dev:version directly.' This tells agents exactly when to reach for this tool and when to go elsewhere.

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