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

With annotations already declaring openWorldHint=true and destructiveHint=false, the description still adds substantial head-of-call context: the $19 launch credit, the one-PR-per-repo-per-directory safeguard, the separate PR opened on the user's own repo (never a fork) with named files, which directories wait for a merge, and the GitHub-auth error path. Note a mild tension with idempotentHint=false — the description asserts repeated calls are safe for PR creation — but this narrows rather than contradicts the hint.

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-loaded with the purpose and mostly free of filler, but it is a single dense paragraph mixing outcomes, billing, PR mechanics, and consent. It is appropriately sized for a tool this complex, though the wall-of-text form makes scanning harder than bulleted structure would.

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?

There is no output schema, and the description compensates by explaining the return shape ('Per directory the result says what happened') and the error/retry contract. Combined with the billing, consent, and merge-gating details, an agent has everything needed to invoke this correctly.

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 100%, so baseline is 3, and the description slightly exceeds it: it explains what omitting `directories` does and justifies the consent_star constraint (the awesome-remote-mcp-servers list rejects PRs from accounts that have not starred it), which is meaning beyond the schema's wording.

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 first sentence gives a specific verb and resource: 'File a saved server in MCP directories.' The described scope (per-directory publishing with distinct outcome modes) is concrete and distinguishable in concept, but it never explicitly contrasts with siblings like add_server or sync_server, so an agent must still infer the boundary.

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?

It states exactly how to scope the call ('Leave `directories` out to send to every directory that fits and is ready, or pass ids from list_directories to pick some') and points to list_directories/list_servers for inputs. It also gives the precondition for consent_star and the recovery path when GitHub access is missing, which is genuine 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.