Review a cover letter against a fixed checklist, read example letters for a role, and open the finished letter in the ResumeNext cover letter editor.
Scored across 3 tools
Each tool targets a clearly distinct purpose: finding examples (retrieval), preparing an editor link (action/handoff), and scoring (analysis). There is no realistic way to confuse them, and the descriptions reinforce the boundaries by noting that scoring stores nothing while the editor stores the letter.
All three names use snake_case with a consistent verb_noun (verb_object) pattern: find_cover_letter_examples, prepare_cover_letter_editor, score_cover_letter. The convention is predictable and readable throughout.
Three tools is on the lean side, but they map cleanly to the narrow cover-letter workflow (find examples, score/check, edit-and-export). Nothing feels redundant, though the surface is small enough that it borders on thin for a 'builder'.
The core lifecycle is covered: get examples, evaluate quality, and load a letter into an editor for formatting/export. Minor gaps exist (e.g. no explicit template/builder or saved-letter management beyond the 7-day link), but agents can work around these.
Searches ResumeNext's library of cover letter examples by job title or field. Returns up to two complete example letters with writing tips and a link to each example's page. Without a match, or without a query, returns the list of roles the library covers. The examples use placeholders such as [Company Name] for the details to replace.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | Job title or field to look for, for example "software engineer" or "nurse". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, closed-world, non-destructive. The description adds genuinely new behavior: a cap of two returned letters, the tips and page link included, the fallback role-list response, and the [Company Name] placeholder convention. Only richer return-shape detail is missing.
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 tight sentences, front-loaded with purpose, followed by return behavior and the fallback case. No filler and nothing repeated from 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 carries the return-value burden and does so: count of results, contents, fallback list, and placeholder format. Nothing an agent needs to invoke it correctly is absent.
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 goes beyond the schema by explaining what 'field' means in practice and what happens when the optional role is omitted, which the schema does not state.
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 gives a specific verb and resource — searches ResumeNext's cover letter example library by job title or field — and its retrieval role is clearly distinct from the sibling tools prepare_cover_letter_editor and score_cover_letter. An agent can select it without inspecting any schema.
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?
It states the calling conditions well: supply a role to search, or omit it / get no match to fall back to the full role list. It does not explicitly name when to prefer a sibling tool instead, but the usage context is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Creates a private link, valid for 7 days, that opens the ResumeNext cover letter editor with this letter already loaded, ready to edit, format and export. Takes the complete final letter as plain text, plus the company, role and job description when the user gave them. Returns the link and the same review as score_cover_letter. Stores the letter for the link.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | Job title the letter applies for, when the user gave one. | |
| company | No | Company the letter is addressed to, when the user gave one. | |
| job_description | No | The full text of the job posting, when the user supplied it. | |
| cover_letter_text | Yes | The complete cover letter as plain text, from the greeting to the sign-off. Not an outline. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations covering the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description still adds meaningful behavior: the link is private and expires in 7 days, and the letter is stored to back the link. It's a non-idempotent write that persists data, which is usefully disclosed, though it doesn't spell out any auth requirement or storage retention beyond 7 days.
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 tight sentences with the key value (private 7-day editor link) front-loaded, then input expectations, then return value and persistence. No filler or redundancy.
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?
No output schema exists, but the description explicitly says what is returned (the link and the same review as score_cover_letter), and the annotations cover the write/non-idempotent nature. Nothing critical for correct invocation is missing.
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 schema already documents all four parameters and the 'not an outline' constraint. The description largely restates them (final letter as plain text, optional company/role/job description when the user gave them), adding little beyond the schema, so baseline 3 applies.
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 outcome: creates a private 7-day link that opens the ResumeNext editor with the supplied letter pre-loaded, plus returns a review. An agent can distinguish it from find_cover_letter_examples and score_cover_letter without opening either schema.
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?
Usage is implied rather than stated: it says to pass the 'complete final letter' and notes it returns the same review as score_cover_letter, hinting this is a superset of that tool. But it never explicitly says when to prefer this over score_cover_letter or find_cover_letter_examples, nor any usage exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reviews a cover letter with a fixed checklist. Returns a deterministic score out of 100 and, for each check (length, opening line, company and role named, quantified results, leftover placeholders, filler phrases, closing call to action, match with the resume, job description keywords), whether it passes and how to fix it. Takes the complete letter as plain text, plus the company, role, job description and the applicant's resume text when available; checks that cannot be evaluated without them are left out of the score. Stores nothing.
| Name | Required | Description | Default |
|---|---|---|---|
| role | No | Job title the letter applies for, when the user gave one. | |
| company | No | Company the letter is addressed to, when the user gave one. | |
| resume_text | No | The applicant's resume as plain text, when available: lets the review compare the letter with it. | |
| job_description | No | The full text of the job posting, when the user supplied it. | |
| cover_letter_text | Yes | The complete cover letter as plain text, from the greeting to the sign-off. Not an outline. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the description correctly spends its words elsewhere: deterministic scoring, graceful degradation when optional inputs are missing, and 'Stores nothing' (a privacy guarantee not derivable from annotations). It does not mention latency, rate limits, or failure modes, keeping it short of a 5.
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-loaded with the action and the return, then the checklist, then the input contract. Two dense sentences with no filler, though the long parenthetical checklist stretches the first sentence.
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?
No output schema exists, and the description fully compensates by describing the score scale and the per-check pass/fix result. Combined with the input contract and the no-storage note, an agent has everything needed to call this 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 baseline is 3, but the description adds meaning the schema does not: which checks consume resume_text and job_description and the consequence of omitting them (those checks are dropped from the score). It stops short of per-parameter format guidance.
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 ('Reviews a cover letter with a fixed checklist'), the return shape ('deterministic score out of 100' plus per-check pass/fix), and enumerates the checks. An agent can distinguish it from find_cover_letter_examples and prepare_cover_letter_editor without opening a schema.
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?
Explains the input contract clearly: the complete letter is required, while company, role, job description and resume are supplied 'when available' and 'checks that cannot be evaluated without them are left out of the score.' It gives context but never states when to prefer a sibling tool over this one.
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.
find_cover_letter_examplesprepare_cover_letter_editorscore_cover_letter
Add one secure layer between your agents and this server.