dropyour_records_summarySummarise what a GRADUATED app keeps in its queryable store: one line per collection with the number of records and the bytes they occupy. Nothing is downloaded. Levels 1-3 have no store (it needs a backend of its own) and return graduated=false. degraded=true means the backend could not be reached — 'unknown', never 'empty'.
| Name | Required | Description | Default |
|---|---|---|---|
| dropId | Yes | ||
| managementToken | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond the readOnlyHint annotation by disclosing that nothing is downloaded, that levels 1-3 return graduated=false, and that degraded=true means the backend was unreachable and the result is 'unknown', never 'empty'. These behavioral edge cases are exactly what an agent needs to interpret results correctly.
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?
Three sentences deliver the core output, the non-destructive behavior, and the two critical edge cases with no wasted words. The key outcome is front-loaded and the caveats follow in a logical, scannable order.
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 read-only tool with no output schema, the description covers the output shape, the graduated requirement, and the degraded/unknown distinction. It omits managementToken semantics and behavior for invalid or unknown dropIds, so it is not fully complete, but it is largely sufficient for a small summary endpoint.
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 needed to explain dropId and managementToken, but it does not mention either parameter. dropId's purpose is inferable from the name and pattern, but managementToken's role is completely unexplained, leaving the agent without guidance on authentication or parameter meaning.
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 states a specific verb and resource: it summarizes what a graduated app stores, with one line per collection containing record counts and byte sizes. It clearly distinguishes this from sibling tools like dropyour_records_list by focusing on aggregate store metrics rather than individual records. The 'GRADUATED app' qualifier adds essential scope.
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 clearly indicates that the tool applies only to graduated apps and that levels 1-3 have no store, giving an explicit when-not-to-use condition. It does not explicitly name an alternative sibling tool for ungraduated apps or for record-level access, but the context is clear enough for an agent to route correctly in most cases.
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.
Most tools target clearly distinct resources and actions, and descriptions do a good job separating overlapping areas like call/release/status or read_content/read_app_files. The main risk is momentary confusion between publish/replace/release and the two read-content tools, but careful reading resolves it.
All names share the dropyour_ prefix and use snake_case, but the overall pattern is mixed: read_* and list_versions use verb-first naming, while records_list, secret_set, secret_delete, and secrets_list use noun-first naming, and logs/status/whoami are bare nouns. Still readable, but not a consistent verb_noun convention.
23 tools is on the heavy side for a single server and spans several distinct subdomains: drop lifecycle, graduated apps, data, records, secrets, scheduling, and auth. Each tool appears purposeful, but the surface could reasonably be split into focused servers.
The set covers the full drop lifecycle — publish, replace, release, rollback, delete, status, settings — plus graduated app concerns like files, logs, versions, store records, app data, secrets, and scheduling. There are no obvious dead ends for the stated domain.