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

Annotations say readOnlyHint=false and openWorldHint=true but leave the blast radius unclear; the description fills that gap precisely with 'It does not call the Mailercloud API and changes nothing in the account.' It also discloses a PII handling constraint (names, emails, phone numbers, addresses, API keys are forbidden) that appears nowhere in the annotations, and the 'call once' instruction usefully qualifies the non-idempotent hint.

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?

Purpose comes first, triggers second, data constraint third, and the no-side-effect reassurance last — a sensible front-loading order. The PII sentence duplicates the schema's own constraint, which is slightly redundant but defensible for a safety-critical rule.

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?

With no output schema and full schema coverage, the description covers what an agent needs: when to fire, in what order relative to user hand-off, what never to include, and that nothing in the account changes. The only gap is that the return value is never characterized, but for a fire-and-forget logging call that is minor.

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 baseline is 3. The description reinforces the `request` parameter with 'in their own words' and the PII prohibition, but that constraint is already spelled out in the schema, and it says nothing about `term`, `outcome`, or `panel_path` beyond what the schema and its enum already define.

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 ('Log a request the connector cannot fulfil') plus the downstream purpose (so the Mailercloud team can add it). No sibling tool does anything comparable, and the description makes that uniqueness obvious rather than requiring comparison.

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?

Explicitly names the triggering condition ('whenever the user asks for something no tool covers, or the glossary marks the term PANEL, WRAP or not offered'), the required ordering ('AFTER you have given the user the panel hand-off or the nearest alternative'), and the cardinality ('Call it once'). This is about as complete a when/how-to-call instruction as a description can carry.

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