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

The description adds substantial behavioral context beyond the destructiveHint annotation: live registry validation, phantom-name rejection, deprecated-name auto-mapping, per-call limits, door routing, and the sensitive-tier approval workflow (from-now-on vs just-once, call on first ask, card is the yes). This fully discloses operational side effects and approval requirements.

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 paragraphs, each with a distinct purpose: definition, routing, and approval. The sensitive-tier paragraph is somewhat long but contains only relevant operational guidance. Front-loaded purpose sentence makes the main action immediately clear.

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?

Despite having no output schema, the description covers everything an agent needs to invoke correctly: what it does, when to use it, routing restrictions, validation behavior, approval flow, and explicit alternatives. For a security-sensitive mutation tool, no critical context is missing.

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%, so baseline is 3. The description adds extra meaning to tool_name by explaining validation against the live registry, rejection of phantom names, and auto-mapping of deprecated names to successors. This goes beyond the schema's 'exact registry name' wording, though it doesn't clarify other parameters.

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 states the exact verb and resource: 'Grant ONE specific tool to an agent's loadout (tool_access).' It also distinguishes the tool from its main sibling, recalibrate_agent_jd, making it immediately identifiable. No ambiguity remains about what this 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?

Explicit usage triggers are quoted ('give <agent> the <tool> tool'), and clear exclusions are given: connector tools auto-provision, and wholesale capability re-derivation should use recalibrate_agent_jd. The routing rules (one tool per call, human door for writes) further clarify when and how to invoke it.

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