Retrieve matches from a purchased alerts subscription, oldest first after a cursor, with subscription status. Use the subscription ID and token returned by the alerts tool.
Read the matches of a purchased alerts subscription (free; the subscription was paid), oldest first after after, plus its status. Use the subscription_id and token returned by the alerts tool.
| Name | Required | Description | Default |
|---|---|---|---|
| after | No | 0 | |
| token | Yes | ||
| subscriptionId | Yes |
Changes observed during successful MCP inspections.
v0.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry behavioral disclosure, and it does add real context: this is a paid-but-free-to-read operation, results come back oldest first, and it returns both matches and subscription status. Still missing: what a match looks like, page size, token expiry, rate limits, and error behavior.
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?
Two short sentences, front-loaded with the action and followed by the prerequisite. The parenthetical about pricing is slightly awkward but earns its place as cost information; no filler otherwise.
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?
No output schema exists, and the description only broadly says matches plus status are returned. For a cursor-paginated read tool with no annotations, an agent still has to guess the page size, how to advance the cursor (next `after` value), and how credential failures surface.
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 0%, so the description must compensate for all three parameters. It partially does: `after` is framed as an oldest-first cursor and token/subscriptionId are given provenance, but it never explains that `after` is a numeric string defaulting to '0' or what the UUID/token formats imply.
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?
States a specific verb and resource: read the matches of an alerts subscription, plus its status. It is clear enough to distinguish from siblings like tolly_stream_read or tolly_jobs_search, though it never names those siblings or explains the boundary explicitly.
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 gives one real usage precondition — the subscriptionId and token come from another tool — which is useful context. But it refers to 'the alerts tool' without naming it, and that name does not appear among the listed siblings, so the agent cannot resolve the prerequisite; no when-not or alternative guidance is offered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.