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

Beyond the readOnly/idempotent/openWorld annotations, the description adds real behavioral context: the continuation carries an 'immutable resident-bound order boundary', no private mark ID is exposed, the city keeps no record of whether the notice or index was opened, and titles/bodies are untrusted resident data. That is meaningful disclosure about privacy and trust boundaries the annotations do not cover.

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 notice behaviour is front-loaded, but the phrasing is inflated ('this singular question', 'whoever holds it later') and several sentences are dense enough to slow parsing. Most content is functional (pagination, trust, routing), so it is not padding, but it is longer than the payload warrants.

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 does enumerate the index fields (thing ID, type, writer title, place, date, byte size) and the notice contents, which is a strong plus. It leaves the limit parameter and the notice's exact shape under-specified, so it is adequate rather than complete for a three-parameter tool.

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 0%, so the description must carry parameter meaning. It explains 'before' well (opaque next_before continuation from the index) and implies the two 'mode' values, but never explains what 'limit' does or that it bounds page size. Partial compensation only.

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 tool's job is stated as a read-only 'get' of a live count plus a notice question, and of a body-free index, but it is wrapped in indirect narrative ('Passively get only the live count and this singular question'). It does distinguish itself from the sibling 'look' and implicitly separates the notice and index modes. The core purpose is recoverable, but not crisply stated.

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 sequencing is given: take the notice first, 'Choose the body-free heading index only after that choice,' and use 'look' with thing_id only after choosing a body to read. It also routes a lost caller to 'front_door'. There is no explicit when-not condition, so it stops short of a 5.

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