Sends a support message. Agent: no captcha → 402 ($0.10 x402). Human: Turnstile. After the 1st agent message there is backoff: 429 + Retry-After (60s → 2×, 1h cap; resets in 24h).
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | What to call the person writing. | |
| Yes | Where to reply. | ||
| form_ts | Yes | Date.now() of when the form opened (≥2s ago) | |
| message | Yes | What you want to say. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / email / descriptionAdded value: +"Where to reply."Input schema / properties / message / descriptionAdded value: +"What you want to say."Input schema / properties / name / descriptionAdded value: +"What to call the person writing."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses several important behaviors: 402 errors with a cost, captcha handling for agents vs. humans, 429 responses, Retry-After, exponential backoff (60s doubling, 1h cap), and a 24h reset. This goes well beyond a typical tool description, even though the '$0.10 x402' phrasing is slightly cryptic.
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 appropriately short and front-loads the purpose in the first sentence. The remaining sentences are dense but compact; the only structural weakness is the cryptic shorthand such as '$0.10 x402' and '60s → 2×, 1h cap.'
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?
The failure modes are well covered, but there is no output schema and the description never states what a successful send returns or whether any confirmation is produced. It also leaves the agent-vs-human success path implicit, so an agent is not fully told how to achieve a successful call.
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 input schema already documents all four parameters with 100% coverage, so the baseline is 3. The description adds no parameter-level detail beyond the schema's simple descriptions.
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, 'Sends a support message,' is a specific verb+resource statement that clearly identifies the tool's function. It does not explicitly distinguish itself from sibling tools, but none of the listed siblings appear to be support-message tools, so no differentiation is required.
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 gives operational context ('Agent: no captcha → 402', 'Human: Turnstile') that implies an agent will be blocked and a human may need to solve a captcha, but it never states when to choose this tool over alternatives or when not to use it. The usage rule is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools relate to auditing (audit_url, get_audit, run_tab) which might cause confusion, but descriptions clarify the differences. Overall, there is some overlap but each has a distinct role.
Most tools follow verb_noun pattern, but a few (billing, contact, health, api_index) are plain nouns, making the naming inconsistent.
With 14 tools, the server covers core audit functionality plus auxiliary features like billing and health, which is appropriate for its scope.
The server provides tools for auditing URLs, managing tabs, retrieving results, patches, badges, and listing tools. Missing delete/update operations for tabs or audits, but these are not critical for a page audit service.