cos_log_query

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable behavioral context beyond that: it filters to WARN+ severity and returns most-recent-first. This helps the agent understand the data shape and ordering, though it doesn't cover all behaviors like pagination or filtering semantics.

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 a single, front-loaded sentence with no filler. It packs the verb, resource, constraints, and purpose efficiently, earning a perfect score for conciseness and structure.

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?

The tool has 8 optional filter parameters with no schema descriptions, making it a flexible but complex query tool. The description covers core purpose and basic behavior but misses any guidance on parameter usage, filter combination, or edge cases. Even with an output schema present, the agent is left under-informed about how to use this tool effectively.

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%, yet the description provides no information about the 8 parameters. Only 'WARN+' hints at the 'level' filter and 'most-recent first' at ordering, but the agent gets no guidance on 'scope', 'since', 'search', 'trace_id', 'session_id', or 'fingerprint'. The description fails to compensate for the missing schema descriptions.

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 uses a specific verb ('Query'), names the resource ('durable log_events store'), and states key constraints ('WARN+', 'most-recent first'), plus a clear purpose ('what is broken now'). This clearly differentiates it from siblings like cos_metric_query and cos_failure_pattern_query.

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 phrase "the agent's 'what is broken now'" clearly implies this is for diagnosing current problems, but it does not explicitly name alternatives or state when not to use it. The context is clear, though no exclusions are provided.

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