tilla_changesRetrieve every repaired value a key has had since a timestamp, apply them to keep your copy correct, and pass the returned until as the next since.
Every value our checks repaired since since ('YYYY-MM-DD HH:MM:SS') that the key holds, with its value now -
apply them and a kept copy stays correct. Pass the answer's until as the next since. Needs a key.
| Name | Required | Description | Default |
|---|---|---|---|
| since | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is a read-only, idempotent, non-destructive, open-world operation. The description adds meaningful context beyond those annotations by disclosing the key requirement, the pagination pattern, and that applying the returned corrections keeps a kept copy correct.
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 compact and front-loads the returned content before explaining pagination and the key requirement. The phrase about applying corrections is purposeful but slightly indirect, keeping it short of maximally crisp.
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 one-parameter tool with rich safety annotations and no output schema, the description covers the key invocation details: timestamp format, pagination via `until`, and authentication. It could more explicitly describe the response envelope, but it is broadly complete for correct invocation.
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 0%, so the description must carry the parameter meaning. It does so by documenting the `since` format as 'YYYY-MM-DD HH:MM:SS' and by explaining that the response's `until` should be used as the next `since`, though it omits timezone or inclusivity details.
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 identifies a specific resource and scope: values repaired by checks since a given timestamp, with their current values. It is understandable as a corrections/changes feed, though it does not explicitly distinguish this tool from siblings such as tilla_latest or tilla_window.
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 provides useful invocation guidance for pagination by saying to pass the answer's `until` as the next `since`, and notes that a key is needed. However, it does not state when to choose this tool over the many sibling tools or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.