coding_format_code

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

The annotations already carry the core safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false) and the description does not contradict them. The description adds some useful context beyond the annotations by disclosing that calls route through the platform's domain-agent dispatcher under JWT/tenant/company scope. However, it never explains what the destructive action actually modifies, leaving a meaningful gap for a mutation-flagged tool.

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 compact and uses a clean Args block with minimal extra prose. However, the brevity reflects under-specification rather than deliberate economy — the first sentence contributes almost no information and the routing sentence is boilerplate-ish context.

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?

Even though an output schema exists, the tool needs substantially more context: the action's behavior is undefined, both free-text parameters are underspecified despite 0% schema coverage, and the destructive annotation is never explained. For a mutation tool with no parameter descriptions, this is insufficient for confident, correct invocation.

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?

With 0% schema description coverage, the description must compensate, and it only partially does. It labels message as 'Free-text objective' and inputs as 'Optional JSON string of structured inputs,' which adds roles the bare schema lacks. But it gives no indication of what valid structured inputs look like for format_code (file paths, style configuration, target scope), so an agent cannot reliably construct correct inputs.

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 lead sentence, "Run the coding domain agent action `format_code`," restates the tool name (coding_format_code → format_code) without defining what the action actually accomplishes. It never explains what 'format code' means as an outcome — whether it rewrites files, enforces style, or returns formatted text — so the agent must guess the tool's real purpose. The routing detail (JWT, tenant, company scope) explains dispatch mechanics, not what the tool does.

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?

No guidance is given on when to use this tool versus the many close coding siblings such as coding_write_code, coding_propose_changes, or coding_run_command. There are no exclusions, alternative recommendations, or preconditions (e.g., 'use when you need to auto-format a workspace file'). The only context provided is the dispatcher scoping, which does not help an agent select the tool.

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