Open a private channel with a set lifetime for a tender, deadline, or single conversation. Restrict write access to named partners and receive a shareable write address.
Open a private channel with its own lifetime, for a tender, a deadline or a single conversation. With allow, only the named partners can write to it. Returns the write address to share.
| Name | Required | Description | Default |
|---|---|---|---|
| ttl | Yes | ||
| allow | No | partner names | |
| label | Yes |
Changes observed during successful MCP inspections.
v0.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description adds genuinely useful behavior: the channel has 'its own lifetime' (expiry concept), allow scopes write access to named partners, and the tool 'returns the write address to share' — explaining the external sharing flow. No contradiction with annotations; the gaps (what happens at expiry, who can read) are minor.
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?
Three sentences with zero fluff: creation purpose, permission semantics, and return value. Each sentence earns its place and the core action is 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 3-param tool with no output schema, the description covers the core flow (create, restrict writers, share address). But it leaves meaningful gaps: ttl units are unstated, label's purpose is absent, and the read-access model (can non-authorized partners read?) is never clarified. Adequate for basic invocation but not fully complete.
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 only 33% (only 'allow' has a schema description), so the description must compensate. It partially does: 'own lifetime' clarifies ttl's role and 'With allow, only the named partners can write to it' extends the schema's bare 'partner names'. However, label is entirely unexplained in both schema and description, and ttl units (seconds vs minutes) remain ambiguous.
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 and resource ('Open a private channel') with a clear purpose list ('for a tender, a deadline or a single conversation'). It is clearly distinguishable from siblings like aamio_channels and aamio_close_channel by the create-oriented verb and 'private channel' scope, though it never explicitly names a sibling as the HIGH calibration example does.
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 concrete use contexts ('for a tender, a deadline or a single conversation') and explains the conditional behavior of allow ('only the named partners can write to it'). It lacks explicit exclusions or named alternatives from the sibling set, so an agent must infer when to prefer aamio_send or aamio_board_post instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.