Bash

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

Annotations already carry the safety profile (destructiveHint=true, readOnlyHint=false, openWorldHint=true), so the bar is lower. The description adds genuinely useful behavioral constraints beyond the annotations: only allowlisted verification commands may run, only a single command (no chaining), and no shell redirection/pipe constructs. This meaningfully shapes agent behavior without contradicting the annotations.

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 sentences with zero waste: purpose is front-loaded, exclusions and alternatives follow, then invocation constraints. Every sentence earns its place and the structure makes it skimmable for an agent.

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 safety-sensitive nature of a command runner, the combination of annotations (destructive/openWorld), full schema coverage, and the description covers what to run, when to run it, and how to constrain invocations. The main gap is the absence of an output schema and no description of the return format (stdout/stderr/exit code), but for a bash tool this is fairly standard and a minor omission.

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%, so all five parameters (command, cwd, session_id, timeout_ms, workspace_id) are already documented in the schema, warranting the baseline 3. The description adds marginal value by constraining what values the command parameter may take (single, allowlisted, un-chained), but provides no format or syntax detail beyond that.

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 ('Run one allowlisted verification command') with concrete examples (tests, build, lint, typecheck, project script). It also distinguishes itself from siblings by explicitly naming what it is not for (git status/diff, file inspection) and pointing to the correct alternatives, so an agent can route correctly without opening schemas.

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?

Provides explicit when-to-use guidance ('verification command') and exclusions ('Do not use for git status/diff or file inspection') with named sibling alternatives (show_changes, tree, search, read). Also gives hard constraints on invocation style (no &&, pipes, redirects, or shell file readers). Nothing is left to inference.

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