check_stack_drift

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

Annotations already declare readOnly, idempotent, openWorld=false, and non-destructive, so the safety profile is covered; the description still earns credit by adding 'requires no authentication' and stating the return shape (structured JSON report with exact pin commands), which the annotations do not provide. It stops short of describing rate limits or registry-freshness caveats for the '256 live' claim, keeping it below a 5.

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 compact sentences, front-loaded with the verb and read-only nature, then the detection scope, then auth and return type. Every clause carries information 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 output schema, the description does the necessary work of saying it returns a structured JSON report including pin commands; combined with full schema coverage and rich annotations, an agent has enough to call it correctly. It is slightly thin on what the report actually contains (fields, severity levels) and on the '256 live' registry being static or refreshed, which matters for a drift-audit 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 single parameter's schema description already lists all accepted manifest formats, including the newline-separated package list. The description repeats 'package.json, requirements.txt, or .mcp.json configuration string' without adding syntax, size limits, or validation rules, 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?

States a specific verb and resource: a read-only audit of a package.json/requirements.txt/.mcp.json manifest against a live SDK/MCP registry, and names what it flags (major deltas, unpinned @latest, outdated deps). The manifest-wide audit scope implicitly separates it from get_package_stability's single-package focus, but no sibling is ever named, so the differentiation is inferential rather than 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?

Usage is implied by the resource it operates on — you'd call it when you have a manifest or package list to audit — but there is no explicit 'use this when' statement, no exclusions, and no routing to get_package_stability, list_volatile_packages, or get_archived_mcp_replacements. An agent must infer the boundary from the nouns alone.

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