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

With no annotations, the description carries the full burden and meets it: it discloses that emdly injects the owner's credentials (agent never sees the key), that writes are permission-gated by the owner's emdly settings, that custom APIs require {{secret}} placeholders in headers/path/body, and that responses return status, paging/limit headers and a body that is truncated for long payloads and must be paged. That covers auth, authorization, and truncation behavior that an agent could not infer.

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 purpose and the auth guarantee, then usage rules, then parameter specifics — a logical ordering. The parenthetical per-service path examples are dense and useful but long; a couple could be trimmed without losing information. No filler sentences, though.

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, so the description compensates by describing the return shape (status, paging/limit headers, truncated body). Combined with the credential model, permission gating, and per-service path guidance, an agent has everything needed to construct a correct call for a 5-parameter, 1-required 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 coverage is already 100%, so the baseline is 3, but the description adds real meaning: `path` is relative to the service, `app` can be omitted when only one is connected, and `headers`/`{{secret}}` behavior is explained beyond the schema text. It does not add much about `body`/`method` interaction beyond what the schema states, so it lands just above baseline rather than at the top.

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?

Names a specific verb and resource ('Call the API of an app the owner connected') and enumerates the concrete services it covers (Jira, Trello, Airtable, Pipedrive, Intercom, Stripe, custom). It clearly distinguishes itself from the sibling api_list, which only enumerates apps, and the per-service path examples make the scope unambiguous.

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 real when-to-use rules: reads (GET, Jira's POST search, Airtable's listRecords, Intercom's search) always work, while mutations happen only where the owner permitted them on emdly. It routes the agent to api_list/the service skill for paths and limits. It does not, however, tell the agent when to prefer the dedicated siblings (github_read, mail_read, ga4_report, calendar_events) over a raw API call, which is a genuine routing gap.

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