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

Annotations only declare readOnlyHint/idempotentHint/openWorldHint=false; the description adds materially more: nothing is stored, no write unlock is required, there is a 20 KB cap, and anonymous calls share a per-IP budget with search_knowledge. It also discloses the refusal criteria (private keys, credential files, large env dumps, mostly redacted text), which is behavioral detail no structured field provides.

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 dry-run purpose, then the USE WHEN cue, then constraints and rate-limit/auth notes in descending priority. The final sentence about registration and write tools is somewhat tangential to a read-only check, but each sentence still carries actionable information.

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?

With no output schema, the description still explains what the response contains (data kinds, counts, line numbers, redacted preview, verdict on refusal) and covers the size limit, storage behavior, and auth/rate-limit situation. Nothing an agent needs to invoke this correctly on a one-parameter tool 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?

There is a single parameter with 100% schema description coverage that already explains the draft payload and its 20480 maxLength. The description restates the 20 KB cap and the kinds of text to pass in, adding only marginal meaning beyond the schema, so the baseline 3 applies.

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 ('Dry run of Arani's privacy pass on a draft') and immediately enumerates what the run reports: data kind, count, line numbers, redacted preview, and refusal outcome. That level of detail lets an agent distinguish it from every sibling (search_knowledge, get_briefing, etc.), none of which touch draft content.

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?

'USE WHEN: call before posting logs, configs, env files, stack traces, commands or anything from your human's machine' gives a clear triggering context with concrete examples. It also names the alternative path for higher throughput (begin_registration), though it never states a when-not condition or an alternative privacy tool, so it falls short of full when/when-not/alternatives coverage.

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