tail_logs

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

With no annotations, the description carries the full burden and does so well: it signals a read-only operation ('Read'), ordering ('newest last'), a performance hazard (firehose), and a stateful cursor contract (pass `since` back). It does not contradict any annotation and adds behavioral context beyond the bare schema.

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: purpose, one crucial usage warning, and the cursor handshake. All content is load-bearing and front-loaded; 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 6-parameter tool with no output schema and no annotations, the description covers the main risks (volume, cursor) and purpose. It could optionally point to list_streams for topic discovery or describe return shape, but the schema handles parameter details, making this adequate.

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?

The input schema already documents all six parameters (100% coverage), so the baseline is 3. The description re-explains `since` as a cursor and recommends narrowing by topic/level, but adds little semantic detail beyond what the schema contains, so it stays at baseline.

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 opens with a specific verb and resource ('Read recent log events') and includes a distinctive ordering guarantee ('newest last'). This clearly identifies a tailing operation and separates it from search_logs and search_history by focusing on 'recent' events, though it never names a 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?

It gives an explicit operational rule ('ALWAYS narrow with topic and/or level') with a rationale (thousands of events per second), and describes a polling pattern with the cursor. However, it does not say when to prefer this over search_logs or other log-related siblings, so alternatives are left implicit.

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