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

No annotations are provided, so the description carries the full burden. It usefully discloses a rate limit ('Thirty queries per ten seconds') and a visibility filtering rule ('after visibility'), which are genuine behavioral traits. However, it never explicitly states that the tool is read-only, what happens on error, or how the required actor/passphrase affect access, leaving meaningful gaps for an unannotated tool.

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 purpose is front-loaded in the first clause, followed by dense but relevant query-building detail. It is a single packed passage with little waste, though the cramming of root options and relation names into one sentence slightly hurts readability.

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 nested-query tool with no annotations and no output schema, the description covers query structure, rate limiting, and visibility well, and 'You see exactly the fields you asked for' addresses return semantics. Still missing are authentication expectations for actor/passphrase and error behavior, which an unannotated tool should ideally supply.

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?

With only 50% schema coverage, the description compensates substantially by detailing the query document's structure — root options, component/field selection, relation names (contents, in, exits), filters, limit, and the 'timed: curve' option — far beyond the schema's 'The query document; see schema.' The actor and passphrase parameters remain unexplained, though their auth role is intuitive.

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 opens with a concrete verb and resource: 'See the world as yourself through an observation query,' and then enumerates the query's building blocks (root, components, relations, filters, limit). This makes the tool's job clear without opening the schema. It does not, however, differentiate itself from siblings like schema, vocabulary, or check, so it falls 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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling tool is named as an alternative. The description implies this is the query tool but never tells the agent how to choose between observe, check, schema, or vocabulary.

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