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

Annotations declare this is not read-only and is open-world but say nothing about latency, cost, or payload. The description fills those gaps: ~50 s wait, a named status enum (completed / waiting_for_approval / running / interrupted), the fact that the account's weekly Muse allowance is consumed, and that pending permission requests may be returned. This is exactly the context annotations cannot carry.

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-loaded with purpose, then return payload, then the escalation path; every sentence carries information. The trailing endpoint trace ('POST /chats or POST /chats/{chatId}/messages, then GET ...') is low-value for an agent choosing a tool and is the only expendable line.

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, so the description must describe the return shape itself — and it does: chatId, status, agent text, created assets with download urls, widgets, and pending permission requests. Combined with the timeout and quota disclosure, an agent has everything needed to call this correctly and handle the partial-result case.

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%, including the email, files, chatId, and message semantics plus the image_1/video_1 naming convention, so the schema already does the heavy lifting. The description restates the chatId new-vs-continue behavior but adds no syntax or constraint detail beyond the schema, making the baseline 3 correct.

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?

Specific verb+resource ('Send a message to Muse ... and get its answer') with a scope qualifier that separates the new-chat and continue-chat modes. It also names the sibling tools it complements (muse_get_chat, muse_list_chats), so an agent can place it in the toolset without opening schemas.

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 branching rule: omit chatId to start a new chat, supply chatId to continue one. It further routes the agent to muse_get_chat (chatId, wait: true, after: lastEventId) precisely when status comes back 'running', which is a concrete when-to-use-alternative instruction rather than an implication.

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