Delimit Social Accounts

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds meaningful context beyond that: 'Calls ai.social.list_twitter_accounts, which scans ~/.delimit/secrets/twitter-<handle>.json files.' This discloses the data source and underlying implementation, letting the agent infer scope (only locally configured accounts) and potential failure modes (missing secret files). It doesn't dwell on edge cases, but it adds real value beyond annotations.

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 uses labeled sections (When to use, When NOT to use, Sibling contrast, Side effects, Args, Returns) that make it scannable and every section earns its place. The opening line states the core purpose, and nothing is redundant or padded. This is an exemplary structure for an MCP tool description.

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 zero-parameter read-only tool, the description covers everything an agent needs: purpose, usage timing, sibling routing, side effects, underlying data source, the fact that there are no arguments, and the return shape ('Dict with accounts list and count plus next_steps'). The output schema exists and the description confirms the return format. Nothing material is missing.

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?

The tool has zero parameters, which carries a baseline of 4 per the rubric. The description explicitly states 'Args: None,' which is genuinely useful — it prevents an agent from hallucinating optional parameters like a platform filter or handle argument that the tool does not accept.

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 opens with a specific verb and resource — 'List configured social media accounts' — and then explicitly differentiates itself from siblings: 'delimit_social_generate drafts; delimit_social_post publishes; this lists who can publish.' An agent can immediately tell exactly what this tool does and how it differs from its direct siblings without opening any 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?

The description provides an explicit 'When to use' section ('to inventory which Twitter/X accounts have credentials available before drafting or scheduling a post') and a 'When NOT to use' section naming the exact alternatives (delimit_social_generate for drafting, delimit_social_post for publishing). This is textbook usage guidance — the condition and the routing are both explicit.

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