Skip to main content
Glama

grade

by net.gradetv
OverviewDiscussionsAdmin

Report play

report_play

Relata se um canal tocou (ok=true) ou não (ok=false + code). Navegador, SO e país saem do pedido, não do corpo. Conta uma vez por dono, por canal, por dia e por resultado; relatar de novo devolve 200 com reason: ja_relatado_hoje, e não é erro. Navegador e sistema saem do User-Agent e o país da borda — mandar isso no corpo não muda nada. Sem relato, o catálogo não aprende: é assim que GET /api/channels/:id/health sabe distinguir canal fora do ar de canal bloqueado para você.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes`true` se tocou, `false` se falhou.
codeNoPor que falhou; só quando `ok` é `false`.
channel_idYesCanal que você tentou assistir.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / channel_id / description
      Added value: +"Canal que você tentou assistir."
    • addedInput schema / properties / code / description
      Added value: +"Por que falhou; só quando `ok` é `false`."
    • addedInput schema / properties / code / enum
      Added value: +[
+  "cors",
+  "geo",
+  "sumiu",
+  "codec",
+  "playlist",
+  "sem_resposta",
+  "protocolo",
+  "sem_stream",
+  "outro"
+]
    • addedInput schema / properties / ok / description
      Added value: +"`true` se tocou, `false` se falhou."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Rich detail beyond the annotations: dedup semantics (counts once per owner/channel/day/result), the 200 + `reason: ja_relatado_hoje` response on re-report, and the statement that browser/OS/country are derived from the request (User-Agent, edge) and ignored in the body. Notably, the idempotent-like re-report behavior adds nuance the `idempotentHint: false` annotation alone would not convey.

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?

Dense but front-loaded: the ok/not-ok outcome and the derived-field rule come first, then the dedup behavior, then the rationale. Every sentence carries information, though the repetition of the User-Agent/país point costs a little.

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 supplies the return contract (200 status, `reason: ja_relatado_hoje` is not an error) and the failure-code linkage. For a 3-param write-report tool, nothing an agent needs to invoke it correctly is missing.

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 real meaning: it clarifies that browser/OS/country are NOT body parameters and that sending them changes nothing, preventing a plausible misuse. `code` applicability ('só quando ok é false') is reinforced.

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 precise verb+resource: reports whether a channel played (ok=true) or failed (ok=false + code). It is clearly distinguishable from sibling `play_reports` (a listing) and ties into `channel_health`. An agent knows exactly what this call does.

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?

Explains the motivating condition — 'Sem relato, o catálogo não aprende' — and routes the agent to the downstream consumer, `GET /api/channels/:id/health`. It does not give explicit when-not-to-use exclusions, but the context for calling it is clear.

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

All grade 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