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

Annotations already declare non-read-only, non-idempotent, non-open-world mutation. The description goes beyond them by disclosing concrete effects: the letter is recorded on the deal, it creates/opens that tommo's work on the deal when none exists (a side effect not captured by any annotation), the recipient sees it immediately, and nothing leaves the workspace. Missing only error/conflict behavior for a non-idempotent write.

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, front-loaded with the core action and its recipient, with no filler. The comma-spliced enumeration of effects ('it is on the deal's record, it opens ..., and the tommo looks at it now') is slightly clunky but compact and information-dense.

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 non-idempotent write with no output schema, the description covers the primary unknowns: where the message lands, the work-opening side effect, visibility, and parameter resolution via list_tommos. It is reasonably sufficient, though it omits failure modes (e.g., invalid deal_id or unresolvable tommo) and never defines what a 'tommo' is for an unfamiliar agent.

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 0% for all four parameters, so the description carries the burden. It usefully resolves the only genuinely ambiguous one — 'to' is a tommo slug or name obtainable from list_tommos — but deal_id, subject, and body are left entirely undocumented, relying on name inference alone.

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 concrete verb and resource ('Write a letter to a tommo of this workspace on a deal'), which is specific and distinguishable from near-siblings like write_the_note_on_a_lead or add_to_the_mail_tommo_wont_read. It does not explicitly name an alternative or the boundary against those siblings, so it falls short of a 5.

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 supplies context (it lands on the deal's record and opens that tommo's work if none exists) and routes the agent to list_tommos for resolving 'to'. However, it never states when to choose this tool over alternatives such as write_the_note_on_a_lead or add_to_the_mail_tommo_wont_read, nor any precondition or exclusion. Usage is implied rather than instructed.

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