Contato ou projeto de produtor ($0.10 x402/crédito por envio). form_ts é o início da composição em ms, entre 2 segundos e 12 horas atrás. Após o 1º envio: 429 + Retry-After.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Como chamar quem escreveu. | |
| Yes | Para onde responder. | ||
| form_ts | Yes | Início da composição, em milissegundos Unix: entre 2 segundos e 12 horas atrás, obrigatório também para agentes. | |
| message | Yes | O que você quer dizer. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / email / descriptionAdded value: +"Para onde responder."Input schema / properties / form_ts / descriptionAdded value: +"Início da composição, em milissegundos Unix: entre 2 segundos e 12 horas atrás, obrigatório também para agentes."Input schema / properties / message / descriptionAdded value: +"O que você quer dizer."Input schema / properties / name / descriptionAdded value: +"Como chamar quem escreveu."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does add useful traits: the cost per send, the required form_ts time window, and the explicit rate-limit behavior “429 + Retry-After” after the first send. It does not describe the success response or auth requirements, but the send/rate-limit behavior is meaningfully transparent.
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?
The description is short and front-loaded with the purpose and cost, then the key timestamp constraint, then the rate limit. Each sentence carries useful information, though the cost expression “($0.10 x402/crédito por envio)” is slightly cryptic.
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?
For a simple four-parameter contact form with fully documented schema fields, the description includes the critical invocation constraints: cost, form_ts range, and rate-limit behavior. It does not explain the success return value, but the absence of an output schema makes that a smaller gap for this tool.
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 baseline is 3. The description repeats the form_ts window already present in the schema and does not add new meaning for name, email, or message beyond what the schema documents.
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 says “Contato ou projeto de produtor,” which identifies the resource/domain but does not state a clear action verb like “send” or “submit.” It gives pricing and constraints, but an agent still has to infer that this is a contact-submission endpoint.
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?
There is no guidance about when to use this tool versus alternatives; no sibling tool is mentioned. It provides technical constraints (form_ts range, 429 after the first send) but not when or why an agent should choose contact over other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool addresses a distinct resource/action: favorites vs. history vs. watch recording are clearly separate, and the NSFW consent/pass tools are unambiguous. Even closely related tools like 'get_channel', 'get_channel_guide', and 'legacy_stream' serve different purposes. No two tools appear to do the same thing.
Most tools follow a verb_noun pattern (get_, list_, create_, add_, remove_, etc.) with clear conventions. A few exceptions exist like 'billing', 'geo', 'health', and 'me', which are nouns and break the pattern slightly, but the overall style is predictable and readable.
With 47 tools, the server is far beyond the typical well-scoped range (3-15). While the API covers a broad domain (auth, catalog, chat, comments, billing, NSFW), this many tools would be better split into smaller, focused servers. The count feels bloated and could overwhelm an agent.
The tool surface is quite comprehensive for a streaming service: it includes auth, user preferences, favorites, history, catalog search, channel details, comments, chat, NSFW consent/passes, billing, and reporting. Minor gaps exist (e.g., no update/delete for categories/groups, no comment editing), but these are not critical dead ends.