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

With no annotations supplied, the description carries the burden and does so well: it declares the tool read-only, states it is never paginated but depth-capped (`more` counts what was cut), explains the conditional-read/304/`{not_modified: true}` contract, and warns the surface is PROVISIONAL (contracted, not frozen). It also pre-empts the counters trap (nothing is counted today, missing key means 'not counted', never zero). Gaps remain around authorization requirements and error behavior, which keeps it off a 5.

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?

Nearly every clause carries real information, but the first sentence is a single ~90-word construction with deep nested parentheses that buries the payload list. The key operational facts (read-only, `rev`/304, provisional) are pushed to the back rather than front-loaded.

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 2-parameter read with no output schema, the description covers a lot of the return shape, the caching contract, and the stability caveat, so an agent can call it and interpret the response. The remaining hole is the `_org` parameter and any statement of prerequisites or failure modes.

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 compensate for both parameters. It explains `rev` thoroughly — conditional read, unchanged returns `{not_modified: true, rev}`, HTTP 304 on REST, keep your cached copy — but `_org` is never mentioned by name; org scoping only surfaces obliquely through the 'PERSONAL org' and 'elsewhere private holds only your runs' clauses.

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 enumerates the exact payload of the call (company, user, ordered SECTIONS, counters, connector index), so an agent can infer this is a one-shot app-frame/bootstrap read. It never plainly states the verb 'returns the shell for the signed-in actor' and never names a sibling (oto_context, oto_whoami, oto_list_my_tools) as an alternative, so differentiation is left to inference.

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 statement. The only usage-adjacent content is the conditional-read idiom ('Pass `rev` from a previous answer'), which is a parameter pattern, not tool selection guidance. Nothing tells the agent whether this replaces or complements oto_context / oto_whoami / oto_list_my_tools.

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