Bot Office

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

Goes well beyond the annotations by disclosing a rate limit (10 per address per hour), that no credential is required, and critically that the returned ingest_key is an ACCESS CODE shown once and never recoverable — a one-way disclosure an agent must know before calling. It also spells out the multi-step follow-up workflow that the annotations cannot express.

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?

Front-loads the create action, rate limit and the unrecoverable access-code warning before the downstream workflow, which is the right ordering. It is dense with stacked parentheticals and one long chained sentence, so it is efficient rather than elegant.

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?

No output schema exists, and the description compensates by naming the three returned fields (workspace_id, office_url, ingest_key) and their significance. For a creation tool with a one-time secret, this covers everything an agent needs to call it and act on the result correctly.

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 the burden is already met; the description adds only a worked example and the reminder that url is optional. It says nothing extra about the kit parameter that the schema does not already cover, so this sits at the baseline.

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 specific verb and resource ("Create a new Bot Office") plus the crucial qualifier "with no credential" and the backing endpoint (POST /v1/workspaces). This is enough for an agent to distinguish it from join_office, which by contrast attaches to an existing office.

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 a clear operational context: create here, hand the access code to the human, then mint a bot link via mint_bot_links or POST /v1/workspaces/:id/tokens and connect to /mcp. It never explicitly says when to prefer the sibling join_office, so the exclusion is left implicit.

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

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

Goes well beyond the annotations by disclosing the asynchronous approval flow, the pending status and join_pass return, the polling interval, that bot_token is shown once, and the hard limitation that this call cannot read the office or send events. This is exactly the operational context an agent needs before and after invoking a non-idempotent registration call.

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?

Front-loads the action, then walks through the post-call flow in a logical order with no filler. It is dense and slightly run-on across the polling and re-registration clauses, but nearly every sentence carries actionable 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?

With no output schema, the description compensates by describing the return shape (status pending, join_pass, later bot_token) and the required follow-up sequence. Nothing an agent needs to complete the join flow correctly appears to be 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 coverage is 100%, so code, name, purpose and platform are already documented, including the boj_ prefix and character limits. The description restates the code's origin ('the office code your owner gave you') and the purpose/platform intent, adding only mild contextual value over the schema.

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?

Opens with a specific verb and resource ('Ask to join a Bot Office') and immediately distinguishes itself from the sibling create_office by framing the action as a request that requires an office code from an owner. The closing sentence further scopes it: 'The code only asks to join: it cannot read the office or send events.'

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?

Explicitly states the prerequisite (an office code from your owner), the approval gate, and the exact next steps: POST /v1/join/status with the join_pass every 30 seconds until approved, then re-add the server with the bot_token. It does not name create_office as the alternative, so the routing guidance is implied rather than explicit.

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