propose_connection

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

With no annotations, the description carries the full burden and does so well: it discloses the key non-mutating behavior (proposal pending user approval), the approval surface (chat/Conexiones), and auth handling (user logs in on approval for remote servers). Rate limits and return format are not covered, so not a 5.

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?

Front-loads the crucial 'does NOT add' fact, then uses tight bullets for remote vs local vs note. Dense but every line carries actionable information; minor redundancy between the note bullet and the closing instruction.

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?

An output schema exists, so return values need not be described, and the description covers the behavioral and parameter essentials for a 7-param, zero-coverage proposal tool. Remaining gaps (exact approval mechanics, error cases) are minor against that coverage.

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 coverage is 0%, so the description must compensate, and it does — explaining url, command, args, env, headers, and note with concrete examples (npx/uvx invocations, {"GITHUB_TOKEN": "…"}). Only 'name' and some edge details are left unexplained, so strong but not exhaustive compensation for seven undocumented params.

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?

States a specific verb (propose/add) and resource (MCP server to brain's Connections), and crucially clarifies that it does NOT actually add the connection — the user approves it. An agent can distinguish this from list_connections or refresh_connectors 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.

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

Gives clear operational context: remote servers use url, local servers use command+args, and it tells the agent to ask the user when a value (e.g. an API key) is missing before proceeding. No explicit when-not or named alternatives, but the usage model is well defined.

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