gc_mail

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It provides none. The tool clearly has side effects (add_endpoint, remove_endpoint, seed_rules, backfill_senders are mutating operations), yet there is no mention of destructive potential, authentication requirements, or what the operations change. Given zero annotation coverage and zero behavioral disclosure in the text, this is a serious gap.

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 a single run-on sentence followed by a comma-separated enumeration of 19 action names. While the length is technically short, it is poorly structured: the 19-action list is undifferentiated and buried, and the opening verb 'Query' mismatches the mutating actions also listed. This is under-specification presented as conciseness, not organized, front-loaded useful content.

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 tool with 20 parameters, 19 actions, and no output schema, this description is grossly incomplete. The agent needs to know which action drives which parameter set, what each action returns, and which actions are read-only vs. state-changing. None of this is provided. A tool of this complexity demands a structured per-action breakdown, which is entirely absent.

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. However, the critical flaw is that the description does not map which of the 20 parameters apply to which of the 19 actions. The description only lists action names; it gives no hint that e.g. 'imap_host' and 'app_key' relate to scan/endpoint actions, 'vat_period' to financial, or 'reason' to dismiss/ignore. This is a significant degradation below the schema-only baseline because the mapping between action and its applicable parameters is entirely absent.

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 lists 19 distinct actions that the tool can perform, covering everything from 'summary' and 'financial' queries to 'add_endpoint' and 'seed_rules' operations. This is not a single coherent purpose but a grab-bag of heterogeneous capabilities. The description does give a specific verb ('Query') and resource ('mail transceiver'), but the scope is so broad it fails to communicate what the tool fundamentally does or why the agent would choose it over siblings like gc_banks, gc_cash, or gc_records.

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 whatsoever about when to use the various actions. The description simply enumerates the action names without explaining which scenario triggers which action. No exclusions or alternatives are mentioned, despite the tool overlapping conceptually with gc_banks (financial) and gc_cash (financial tracking). An agent is left to guess which of 19 actions is appropriate for a given request.

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