Mushi — where to start

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it explicitly says 'Read-only; does not call any downstream tools itself,' which is a meaningful guarantee for an agent deciding whether to invoke it. It also discloses that hidden tools are named with enablement instructions, which is a useful behavioral trait not visible in the schema or annotations.

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 description is front-loaded with the most critical instruction ('CALL THIS FIRST'), then the return contract, then the scope constraint, then the safety note. Every sentence earns its place: the examples are compact, the return format is enumerated, and there is zero filler. It is appropriately sized for a tool that needs to orient an agent.

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 read-only orientation tool with one optional parameter, no output schema, and no nested objects, the description is complete. It explains what the tool returns (three enumerated items), how to use it (intent phrase or blank), what it does not do (no downstream calls), and how it handles hidden tools. An agent has everything needed to invoke it correctly without further context.

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 schema already documents the single 'intent' parameter well. The description adds value by giving concrete example values ('fix the top bug', 'check what I should work on', 'run QA tests', 'set up Mushi') and clarifying that leaving it blank yields a general orientation. This goes beyond the schema's examples and clarifies the blank case, which is genuinely useful.

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 states a specific verb ('CALL THIS FIRST'), a clear resource (Mushi project orientation), and a precise scope: it returns a curated list of 5–12 relevant tools, a one-paragraph orientation, and a single recommended first tool. It also explicitly distinguishes itself from the 40+ sibling tools by being the entry point when unsure which tool to use, so an agent can tell it apart 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?

The description gives explicit when-to-use guidance: 'CALL THIS FIRST if you are new to this Mushi project or unsure which tool to use.' It also provides concrete example intents and states what it avoids (loading the full tool catalog), which implies when not to use it (when you already know the exact tool). This is strong routing guidance relative to the large sibling list.

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