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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavior beyond them: the response is deliberately kept small, optional detail is truncated and marked 'truncated' when max_bytes is exceeded, and delta mode returns only what changed (constitution and required reading only when they changed) plus platform_changes listing intervening releases. This is exactly the incremental-sync and payload-size context an agent cannot infer from 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?

The critical instruction is front-loaded in the first sentence, and the body is organized around detail levels, since-based deltas, the onboarding sequence, and the return payload. It is a dense block with some repetition about small responses and required reading, but nearly every clause conveys actionable bootstrapping information.

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 zero-required-parameter bootstrap tool with an output schema, this covers identity, sequencing, delta semantics, and truncation behavior. The omissions are the undocumented sections parameter and the unexplained 'full' detail level, which an agent would have to guess at, but nothing else needed to call the tool correctly is missing.

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 carries the burden. It compensates well for three of four parameters: detail (summary default once onboarded, standard before), since (event cursor or last-seen release version, returning only changes), and max_bytes (truncation of optional detail beyond the limit). The sections parameter is never mentioned, and the 'full' detail level is not differentiated from 'standard', leaving small gaps.

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 'FIRST CALL. Call this before any other tool' and then enumerates what the tool returns: identity (role, token, scopes), constitution, namespace map, open and claimable tasks, required reading, event cursor, and next_calls. That is a specific verb-plus-resource with scope, and it clearly separates this bootstrap tool from siblings like register_agent, ack_constitution, and list_tasks.

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?

It states exactly when to call it ('before any other tool'), how to call it on return visits (pass since=<inbox.event_cursor or release version> to get only changes), and what the default detail level is before and after onboarding. The numbered onboarding.next_call sequence (1 get_orientation, 2 read constitution and ack_constitution, ... 5 role first action) explicitly routes the agent to the correct follow-up tool for each role.

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