Skip to main content
Glama
Sign In

remoet-mcp

by io.github.remoet-labs
OverviewDiscussionsAdmin

View Company Details

get_listing
Read-only

Works without a Remoet account. Get detailed information about a specific company listing by its slug. Use this to review a company before deciding whether to star it. Returns the company's full description, perks, job count, and URLs. hiringStats shows how often the company opens roles and how long roles stay listed, counted in distinct roles: newRoles30d/newRoles90d (roles posted in the window, by the board's own publish date where it gives one, else when Remoet first saw the role), closedRoles90d (roles taken down), and medianDaysListed (median days from posting to takedown, over medianSampleSize roles closed in the last 180 days). A takedown is not a confirmed hire, so report how long roles stay listed, never a time to hire. A null count means Remoet cannot answer it honestly: tracking began inside the window (see trackedSince), or most of the board came down at once (a dead board or broken source) so the closed count is unknown. A null median means fewer than 5 closed roles or under 180 days of tracking. monthly[] has newRoles and closedRoles per UTC calendar month, oldest first, up to 12; the last month is the current, partial one, and months before tracking began are left out (closedRoles is null in a month with a board event). salaryStats gives pay bands over the company's live roles on the public board that state a salary (rolesWithSalary; it can be lower than jobCount, which also counts roles Remoet does not publish): bands[] has label 'all' plus 'junior'/'mid'/'senior' where at least 5 roles back it, each with medianFrom, medianTo, p25From, p75To and sampleSize. medianTo and p75To are null when fewer than 5 of those roles state an upper figure: there is no honest top to quote, not missing data. Figures are stated salaries converted to USD a year, not salaries posted in USD; say so when quoting them. NOTE: the tech stack is a small preview unless the company is starred. Starring unlocks the full stack (techStackCount shows the true total, e.g. a 3-tag preview of 147). Pass checkTechStack with the user's technologies to verify overlap against the FULL stack. Matched ones come back in matchedTechStack and lead the preview, same contract as search_listings. The star budget is reported by get_account.

Input Schema

NameRequiredDescriptionDefault
slugYesThe URL slug of the listing (e.g. "digital-ocean", "stripe")
checkTechStackNoTechnologies to verify against the company's full stack (auto-normalized, max 50); matches are returned in matchedTechStack

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / checkTechStack / items / maxLength
      Added value: +100
    • addedInput schema / properties / slug / maxLength
      Added value: +500
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover the read-only, closed-world safety profile, and the description adds substantial behavior beyond that: no account is required, null counts and null medians each have a distinct meaning, a takedown is explicitly not a confirmed hire, salary figures are USD-converted stated salaries, and the tech stack is a truncated preview unless the company is starred (with the star budget owned by get_account). These are exactly the caveats an agent would otherwise get wrong.

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 account-free access and the one-line purpose, then caveats in descending importance. The hiringStats and salaryStats passages are dense, run-on prose that would scan better as bullets, but essentially every sentence carries non-redundant output semantics that have no other home given the absence of an output schema.

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 must carry the entire return-value burden, and it does: it enumerates hiringStats, monthly[], salaryStats bands and techStack preview semantics, including when fields are null and why. An agent can call this correctly and report results honestly without further information.

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 the baseline would be 3, but the description adds real meaning the schema cannot: checkTechStack is verified against the FULL stack rather than the preview, matches surface in matchedTechStack and are promoted into the preview. Slug semantics are left to the schema's example, which is fine given full coverage.

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?

States a specific verb and resource ('Get detailed information about a specific company listing by its slug') and immediately disambiguates from siblings by framing it as the review step before star_listing and by referencing the shared contract with search_listings. An agent can tell it apart from search_jobs/search_listings 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.

Usage Guidelines4/5

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

Gives a concrete usage condition ('Use this to review a company before deciding whether to star it') and an explicit instruction for the optional parameter ('Pass checkTechStack with the user's technologies to verify overlap against the FULL stack'). It does not name the sibling to use for discovering a slug in the first place, nor state exclusions, so it stops short of full when/when-not guidance.

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

All remoet-mcp 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