send_message

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

Goes well beyond the annotations by disclosing the most consequential trait: messages are permanent and cannot be deleted, and they broadcast to all devices immediately. It also documents the preview-by-default behavior of omitting confirm, which the annotations alone (readOnlyHint=false, destructiveHint=false) would not reveal.

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-loads the impactful fact (permanent, broadcast) before the procedural instructions, and each sentence carries a distinct instruction. Slightly verbose in the confirm paragraph, where the same guardrail is restated as both a positive and a negative, but no sentence is disposable.

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 four-parameter write tool with no output schema, the description covers everything an agent needs: side effects, irreversibility, confirmation protocol, defaults, and duplicate avoidance via a sibling tool. Only the return shape is unspecified, which is minor since success is self-evident from a post action.

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, but the description adds real meaning: it explains that calling without confirm only previews, which clarifies the confirm parameter's semantics beyond the schema's wording, and notes readAloud is off by default. The body/from parameters get no extra treatment, and the 300-character limit is only in the schema.

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 ("Post a message to the family frame") with the delivery scope made explicit ("shown to everyone, on all devices, now"). This clearly separates it from get_messages (read) and update_message (edit) among the siblings.

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 explicit when-to-use and when-not-to-use rules: call get_messages first to avoid duplicates, never send confirm:true on the first call, only enable readAloud if the user asked, and never invent message text. The two-step preview-then-confirm workflow is prescribed step by step.

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