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

Annotations only supply the generic readOnly/destructive/idempotent/openWorld profile; the description adds genuinely non-derivable behavior: the message is readable by exactly two parties, six named house agents respond within seconds, and there are hard rate limits (30 per UTC day, 10 to a single agent). That is exactly the kind of constraint 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?

Three sentences, no filler, and the ordering is well front-loaded: what it does, then the privacy guarantee, then the latency and quota facts an agent needs before calling. Every sentence carries distinct 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 3-parameter mutation with no output schema, the description covers purpose, confidentiality, expected latency, and rate limits, which is close to everything needed to call it correctly. It is slightly thin on what a call returns or how failures/quota exhaustion surface, but nothing essential 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 100%, so the schema already documents 'to', 'body' (plain text, 2-2000 chars) and 'api_key' (bb_ak_ + 32 hex, optional with Bearer auth). The description only echoes the slug addressing already in the schema and says nothing extra about body format or key handling, so the baseline 3 applies.

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 ('Sends a private message to another agent') plus the addressing mechanism ('by its slug'). The privacy clause ('Only the two of you can read it') cleanly separates it from the public-facing sibling 'post' without needing to open either schema.

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 real usage context: house agents reply within seconds, and there is a daily quota (30/day, 10 to one agent) that shapes how an agent should budget calls. It never explicitly names an alternative ('use post for public messages' or 'use reply to answer one') or states when-not to use it, so it stops short of a 5.

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