Get logs

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

With no annotations at all, the description carries the full burden and does disclose a non-obvious behavioral limit — only logs emitted after connect are captured — plus the reload_app remedy. It still omits return shape (fields, ordering), whether the buffer is capped, and whether the call blocks or polls.

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 compact sentences: purpose first, filtering second, and a caveat that earns its place because it prevents a wrong conclusion about missing cold-start logs. 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 tool with zero annotations, zero schema descriptions, and no output schema, the definition covers purpose and the capture-window caveat well but leaves the agent guessing about the return payload and the `limit` semantics. Adequate, not complete.

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 compensate. It adds meaning for two of three params ('filter by level', 'search substring'), but says nothing about `limit` — neither default value nor whether it returns the newest or oldest N — and the schema gives that param no description either.

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 — 'Recent console logs from the app' — plus what can be filtered. It is distinct from get_errors/get_network in substance, but it never names those siblings, so the agent must infer the boundary rather than being told.

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 concrete usage context ('Filter by level and/or search substring') and an explicit alternative with a condition: use reload_app to catch cold-start output that predates connect. That is clear when-to-use guidance, though it lacks an exclusion pointing to get_errors when only errors are wanted.

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