Skip to main content
Glama

Agent Inside

agent_inside

Agent Inside™: the product as a tool the agents people use can call, and inside the skill packs, agent templates and automation nodes they install. Returns which of the product's own surfaces shipped (skill, mcp server, automation node), the targets found in others' repos (a pack, a template, a node or a list; how each takes an addition: pr, issue or email; its status: found, opened, emailed, merged, declined) each with its tagged link, and the rules. add: targets the agent found (kind, name, url, owner, stars, how, note), one per repo. mark: one step for one target by its key or url (opened with prUrl, the PR or issue the founder opened; emailed; merged, recorded as a listing with its campaign so what it brings is read; declined; skip). Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "agent_inside"
  }
}

Input Schema

NameRequiredDescriptionDefault
addNo
markNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=false and destructiveHint=false, so the description's task is to explain the mutation semantics, and it partially does: add ingests targets, and mark's actions are described by effect ('merged, recorded as a listing with its campaign so what it brings is read'). It does not state auth/permission requirements, whether entries can be reverted, or what happens on duplicate adds, so the disclosure is useful but incomplete beyond the annotation set.

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

Conciseness2/5

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

It is a single dense run-on paragraph with colons and semicolons, opening on branding ('Agent Inside™') and closing on 'Free.' — neither helps an agent act. The substantive content is buried mid-sentence rather than front-loaded, and the trademark/pricing language does not earn its place.

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

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested, mutation-capable tool with no output schema and thin annotations, the description leaves important things unresolved: 'the rules' are referenced but never explained, the 'key' identifier format is undefined, and there is no indication of what the default (no-arg) read returns in terms of shape or volume. It communicates the broad concept but not enough for confident invocation.

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 description coverage is 0% and the schema is nested, so the description carries the load and largely does: it lists every add field (kind, name, url, owner, stars, how, note), maps 'how' to pr/issue/email, and explains each mark action enum value including prUrl's meaning. Gaps remain — 'key' is never defined beyond 'its key or url', and 'note'/'stars' get no semantics — but this is meaningful compensation for a schema that documents nothing.

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

Purpose3/5

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

The description does enumerate what the tool touches — the product's own shipped surfaces (skill, mcp server, automation node), targets found in others' repos, and 'the rules' — plus the two operations add and mark. But it opens with a meta marketing framing ('the product as a tool the agents people use can call') instead of a verb+resource, so an agent must read the whole run-on sentence to infer that this is a distribution/outreach tracking tool. It never clearly separates it from named siblings such as shipped.

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

Usage Guidelines2/5

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

There is no explicit when-to-use, when-not-to-use, or alternative tool named. Usage is only implied by the presence of add and mark ('targets the agent found', 'one step for one target'), leaving the agent to guess when this is the right tool versus another surface-tracking sibling.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources