Skip to main content
Glama
Sign In

LinkedNav

by io.github.linglistack
OverviewDiscussionsAdmin

Review profile

review_profile
Read-only

PROFILE REVIEWER: scores a LinkedIn profile the way a SPECIFIC audience would judge it, and writes copy-paste rewrites. Use it for "review / score / improve / audit my LinkedIn profile" (or someone else's, by URL). Reads the profile live from the user's own LinkedIn account, plus the person's recent posts and comments, and returns an overall 0-100 score (computed deterministically from the sections, weighted by the goal), a plain-language summary, top 3 wins and leaks, and eleven sections — photo, banner, headline, about, experience, featured, skills, recommendations, completeness, trust signals, activity (posted or commented in the last 7 days) — each with its score, why, the current text, a ready-to-use rewrite, the score after it, and why it is better; plus projectedOverall if every rewrite is applied. AUDIENCE FIRST: without audience it uses the target customer on the active AI setup; when there is none it returns status "needs_audience" with a question and examples INSTEAD of a score — ask the user that question and call again with their answer in audience. Never score it yourself. Sections LinkedIn does not return here (Featured) are marked unknown and left out of the overall. SAVES NOTHING AND CHANGES NOTHING on the profile: on the user's own profile, each change goes through update_my_profile (preview, then confirm) only after the user says yes to that change.

Input Schema

NameRequiredDescriptionDefault
goalNoWhat the profile must achieve, in the user's words or one of: job, sell-b2b, fundraise, recruit, thought-leadership, career-transition, speaking, other. E.g. "find customers", "get hired", "raise a seed round", "recruit engineers", "thought leadership". Omit: finding customers when the audience comes from the setup.
profileNoThe LinkedIn profile to review: its URL (linkedin.com/in/…) or member id. Omit to review the user's own profile (their connected LinkedIn account).
audienceNoWho must be convinced by this profile, as specific as the user can say (e.g. "VPs of Sales at 50-200 person SaaS companies"). Omit to use the active AI setup's target customer; when there is none the tool asks for it.
connectionIdNoWhich of the user's LinkedIn accounts to read from (and, with no profile, whose profile to review): its id from get_linkedin_accounts. Omit for the first live one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations cover read-only/open-world, but the description still adds real behavior: the score is deterministic and goal-weighted, Featured is returned as unknown and excluded, and nothing is saved or changed. It also discloses the handoff path for actual edits. Lacks detail on cost/latency of the live crawl of profile plus posts/comments, which is the main remaining unknown.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the role and the action, then triggers, then output shape, then safety. It is dense and long — the eleven-section enumeration is the main bulk — but nearly every clause carries operational information rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

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 contract: overall 0-100, summary, top 3 wins/leaks, eleven named sections each with score/why/current text/rewrite/new score, plus projectedOverall, and the needs_audience status. Combined with the audience fallback and the no-write guarantee, an agent has everything needed to call and interpret it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 semantics the schema does not: omitting `profile` means the user's own account, omitting `audience` triggers the needs_audience flow rather than silently defaulting, and `goal` weights the section scoring. That is behavior beyond field documentation, though `connectionId` implications are only lightly touched.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a concrete verb+resource+scope: scores a LinkedIn profile as a specific audience would judge it and produces copy-paste rewrites. It is clearly distinguished from the read siblings (get_profile, get_my_profile) and from the mutating sibling (update_my_profile), which it explicitly delegates writes to.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives literal trigger phrases ('review / score / improve / audit my LinkedIn profile') and covers the third-party case by URL. It also states the audience fallback rule: without `audience` use the setup's target customer, otherwise expect status "needs_audience", ask the user, and re-call. There is no ambiguity about when to invoke or how to proceed.

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

All LinkedNav toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources