Bash

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

Annotations declare destructiveHint=true and readOnlyHint=false, so the mutation/destructive nature is covered by annotations. The description adds valuable context the annotations don't: the async durable run-id behavior in execution_mode=auto, the prohibition on command chaining, and the return-immediately semantics. This adds meaningful behavioral detail beyond what annotations offer.

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?

Description is compact and front-loaded with the core action. The four sentences are each purposeful: primary action, async behavior, post-error handling, exclusions. Slightly dense but no redundancy or filler. Very close to a 5, though the multiple clauses about async behavior could be simplified.

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 tool with 11 parameters, 100% schema coverage, an output schema, and strong annotations, the description covers the key operational guidance: async vs sync, which results to fetch, what's forbidden, and what to use instead. The output schema handles return-value documentation. Complete enough for effective agent use given the rich schema and annotations.

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 11 parameters are already documented in the schema. The description adds no per-parameter detail beyond the schema. However, the description adds top-level semantics (async behavior, no chaining) that relate to parameters like execution_mode, though these are already partially covered in the schema enum descriptions. Baseline 3 is appropriate given the schema carries the parameter burden.

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?

Description states 'Run one allowlisted verification command' — a specific verb+resource with clear scope. It distinguishes from siblings by explicitly excluding git/file-inspection tasks and directing those to show_changes, tree, search, and read. The execution_mode=auto async behavior is also clearly described.

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?

Highly explicit guidance: tells when long commands become async, instructs to use run_task_status and read_run_task_result after transport errors, explicitly forbids chaining with &&/pipes/redirects, and names specific alternative tools (show_changes, tree, search, read) for non-bash operations. This is comprehensive 'when/when-not' guidance that directly improves agent behavior.

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