trmnl_get_device_logs

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: newest-first ordering, the two log sources, and cursor-based back-paging. It says nothing about retention window, rate limits, or entry structure.

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?

Four short sentences, front-loaded with the purpose and ordering, with the pagination note where it is needed. The phrasing 'What rendering for it logged' is slightly garbled and the raw endpoint path adds little for an agent, but there is no filler.

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 nested-schema read tool with no output schema, the description covers ordering and pagination but not what a log entry contains, what 'source' values exist, or how level filtering behaves. An agent can call it, but cannot fully anticipate the response or filter confidently.

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 only 33%, and the description compensates for the two cursor parameters by explaining they come from the last returned row. That is real added meaning, but 'source' and the filtering semantics of 'level' remain unexplained in both schema and description.

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 logs of a device', and clarifies the content as device-reported plus render-time log entries. It is distinguishable from trmnl_get_plugin_setting_logs by subject (device vs plugin setting), though it never names that sibling 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?

Usage is implied rather than stated: you call it to inspect a device's logs, and the description explains how to page further back using before_ts and before_event_id from the last row. There is no explicit when-to-use vs when-not, no mention of the plugin-log sibling, and no prerequisites.

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