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

Beyond the destructiveHint annotation, the description discloses important async behavior: the tool only queues a sticky note, does not wake the host, does not type into their UI, and requires the session to poll. It also adds write-tier approval context ('first use may require a manager's approval', 'the card is the yes — do not re-ask in chat'), which is meaningful operational context not available from 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 dense but well-organized: the core queueing semantics and usage triggers are front-loaded, and the approval caveat is isolated in a separate bracketed block. Every clause adds useful context, though the write-tier block is slightly elaborate for a tool description.

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?

The description covers what the tool does, when to invoke it, how the polling model works, how to choose target_session_id, and what approval behavior to expect. For a side-effectful queueing tool with no output schema, the agent has enough to select and invoke it 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 coverage is 100%, so the baseline is 3. The description adds value by explaining that target_session_id must match what the host polls and gives concrete examples (grok-<id>, claude-<id>, grok-bot-<agent-slug>). It also clarifies that instruction should be an imperative, not a transcript dump, which supplements the schema's 'one clear instruction' phrasing.

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 opens with a specific verb and resource: 'Queue a short instruction for an external agent session' and then names concrete host types (Grok terminal, Claude Code, Grok Bot). It clearly differentiates itself from polling/list tools by stating 'Pull sticky only' and adding that FreedomOS does not wake or type into the host UI.

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 trigger phrases ('tell Grok…', 'have Claude…', 'send this to my Grok Bot…') and explains routing intent for CoS. It provides the complementary complementary polling path via 'poll-fo-directives.sh or list_attention_directives' and instructs the agent to 'Pass the same target_session_id the host polls,' making both when-to-use and how-to-use explicit.

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