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

Goes well beyond the annotations by disclosing real side effects: fixed tags "change your preferences now" (a persistent mutation, consistent with readOnlyHint=false and idempotentHint=false), while optional text is "discarded" and "cannot change instructions or policies" — an explicit prompt-injection guard. This is exactly the behavioral context an agent cannot get from the structured fields.

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 short, front-loaded sentences that each carry distinct information (action, side effect, text handling). The telegraphic phrasing ("now", "discarded") is terse but never ambiguous, and nothing is redundant.

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?

Covers what the tool does, the persistence consequence of tags, and the neutrality of text — enough for a 4-param, no-output-schema tool. It omits what the call returns and any indication of whether tags must relate to the rated reply, which keeps it just under complete.

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 only 25% (session only), so the description must compensate, and it does: it conveys the rating range, that tags are fixed and effective immediately, and that text is optional and not acted upon. The one gap is that the tag enum values (e.g. "ember-shrine", "koso-tower") are never explained.

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 ("Rate a host reply from 1 to 5") and names the rating scale, so the agent knows this is a feedback-capture tool rather than a read tool like read_guestbook or a free-text note like leave_note. It never explicitly contrasts with those siblings, so it stops short of a 5.

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?

The phrase "Rate a host reply" implies the trigger (after receiving a host turn), which gives implied usage guidance. However, there is no explicit statement of when to prefer this over leave_note or tip, and no exclusion conditions, leaving the agent to infer the boundary.

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