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

With no annotations, the description carries the full burden, and it does disclose one important behavior: 'A person reads it,' telling the agent this is a human-reviewed, not automated, channel. It does not say whether submissions are anonymous, whether the sender gets a reply, or any rate/abuse constraints, and the existence of an output schema means return values need not be described.

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 sentences, front-loaded with the action and its purpose, followed by the routing exclusion and the parameter hint. No filler; the only softness is the conversational phrasing, which costs little.

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 three-parameter submission tool with a full output schema, the description covers purpose, the key alternative, and when to supply the optional word/language fields. Only the post-submission behavior (confirmation, reviewer follow-up, anonymity) is left unstated, which is a minor gap given the output schema.

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%, so text, lang, and message are already documented, and the enum for lang is constrained in the schema. The description adds only a light conditional ('name the word and the language when the note is about one entry'), which implies the two optional fields travel together but adds little beyond the schema's own 'when it is about one' wording.

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 concrete action and recipient ('Send the people who make immit a note') and enumerates the three things that qualify as feedback: a wrong entry, a badly behaving tool, a missing field. A reader immediately knows this is a feedback channel, and the sibling report_missing_word is explicitly carved out.

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?

Gives an explicit routing rule: for a word with no entry, use report_missing_word instead, which is the main ambiguity among the siblings. It also says to name the word and language when the note concerns one entry. It does not cover the other siblings (lookup_word, search_words, conjugate), but those are obviously non-overlapping.

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