check_stack

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

No annotations are present, so the description carries full burden. It is exceptionally transparent: explains that versions are compared in-process, only project slugs are sent upstream, never calls the /v1/upgrade endpoint, does not log on hosted endpoint, and cannot verify versions. It also discloses edge-case behavior like tracked:false, ignored target_version, and applies_if precondition logic.

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 a single dense paragraph lacking any formatting (bullets, sections). While every sentence carries information, the wall of text is difficult to parse and repeats some schema details (e.g., target_version behavior). It would benefit from structured breaks to improve scannability, especially for an AI agent parsing 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?

Given the tool's complexity (multi-component checks, modes, filters, no output schema), the description is remarkably complete. It explains return behavior, default briefing, how facts are grouped, severity filtering, and the privacy model. There are no significant gaps that would leave an agent uncertain about what the tool does or returns.

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% (baseline 3), but the description adds meaningful semantics beyond the schema. For example, it elaborates the briefing logic (action_required vs check_config, applies_if resolution, group-max severity merging) and clarifies the audit purpose of version_source. It does not cover every parameter interaction, but it substantially enriches understanding.

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 specific verb+resource: 'Check the user's running component versions against known facts.' It clearly distinguishes itself from siblings by explaining its unique role (version comparison, upgrade path) and explicitly references 'get_release' and 'facts_by_entity' for drill-down, making its niche clear.

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 provides strong context on when to use the tool (checking a running stack) and how to tailor it via detail, target_version, and severity_min. It references alternatives at the end ('Drill down with get_release or facts_by_entity'). It does not explicitly state exclusions (e.g., 'use list_facts instead when...') but the guidance is sufficient for an agent to choose it appropriately.

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