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

Annotations already declare destructiveHint=true, so the risk profile is partly covered. The description adds genuinely useful context beyond that: the command is arbitrary, it executes on the server, and it runs in the site's working directory. It does not disclose permissions required, whether execution is synchronous, how output/failure is surfaced, or any rate limits.

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?

Front-loaded with the warning and the core action in a single tight sentence, with the caution adjacent. The trailing 'Forge v2: POST /orgs/...' endpoint is implementation detail that consumes space without helping an agent decide or invoke, keeping it short of a 5.

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 destructive, arbitrary-command tool with no output schema and annotations covering only destructiveness, the description covers the essentials (what runs, where, with a caution) but omits what comes back, whether the call blocks, and how failures are reported. Adequate but with clear gaps.

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% with all four params documented, including an example command, so the schema carries the load. The description adds only the REST path showing how organization/server/site/command map to URL segments, which is marginal. Baseline 3 per the coverage rule.

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 (Runs), resource (an arbitrary shell command), and scope (in the site's directory on the server). No sibling in the list executes commands, so the agent can distinguish it immediately from forge_deploy_site and the get_* tools.

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?

Only guidance is the generic warning 'Use with care.' There is no statement of when this is the right tool versus forge_deploy_site or forge_get_deployment_log, nor any exclusion about when not to use it. The caution flags risk but does not route the agent.

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