Write a resignation letter from your details in a standard, formal or grateful style, with a link to edit it and save it as PDF, DOCX or TXT.
Scored across 1 tool
There is only one tool, so there is no possibility of confusing it with another. Its purpose (generate a resignation letter in one of three named styles) is stated unambiguously.
With a single tool, the snake_case verb_noun name 'write_resignation_letter' is clear and self-describing. There are no other names to be inconsistent with.
One tool is slightly thin relative to the 3-15 guidance, but the server's scope is a single narrow task (drafting one letter), so a single tool genuinely earns its place rather than being an arbitrary split.
The tool covers the full lifecycle for a stateless generator: input details, style selection, full letter output, and an editable link, with no persistence operations needed since it stores nothing. Minor gaps like no style-listing or letter-variation operations remain, but nothing blocks the core workflow.
Writes a resignation letter from the user's details in one of three styles: standard (Professional and neutral. The safe default for most resignations.) formal (Short, on the record, notice-period wording. For HR files and strict processes.) grateful (Warm and personal. For a manager and a team you want to keep in your network.) Returns the complete letter text and a link that opens the same letter in ResumeNext, ready to edit and save as PDF, DOCX or TXT. Template-based and deterministic. Stores nothing.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | The user's current job title. | |
| style | No | Letter style. Defaults to standard. | |
| company | Yes | Employer the user is resigning from. | |
| last_day | Yes | Last working day as it should read in the letter, for example "March 14, 2026". | |
| your_name | No | The user's full name, for the sign-off. | |
| manager_name | No | Name of the manager the letter is addressed to. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavior: it is template-based and deterministic, it stores nothing, and it returns both the full letter text and a ResumeNext edit/export link (PDF, DOCX, TXT). That is real context beyond the 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?
One dense paragraph, front-loaded with purpose, then style semantics, then return value and side-effect guarantees in the last two sentences. The inline style glosses are long but each earns its place by disambiguating the enum; nothing is redundant with the schema.
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, the description correctly specifies the return payload (full letter text plus an editable/saveable link). It also covers the no-storage/privacy posture for a document about a personal career event. Minor gap: it does not say what happens to omitted optional fields (role, your_name, manager_name), leaving the agent to guess whether placeholders are inserted.
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 would be 3, but the description goes further by defining what each of the three style enum values actually means and which situation each suits, which the terse schema enum does not convey. It leaves the required company/last_day and the name fields to the schema, which is adequate at full coverage.
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?
Opens with a specific verb+resource ('Writes a resignation letter') and immediately scopes it to three named output styles with one-line characterizations of each. An agent knows exactly what artifact it will get and which variant is being produced; no siblings exist to confuse it with.
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 per-style selection guidance with concrete conditions: standard as 'the safe default for most resignations', formal 'for HR files and strict processes', grateful 'for a manager and a team you want to keep in your network'. That is actionable routing for the one real decision in this call, though there is no explicit when-not-to-use or alternative-tool guidance (none exists).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
write_resignation_letter
Add one secure layer between your agents and this server.