Metis — Get Spans

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

No annotations provided; description does not state that this is a read-only operation, does not mention idempotency, rate limits, or the definition of 'recent'. Only states it returns a JSON array of span objects with a default limit of 50.

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 extremely concise with a clear purpose statement, structured Args block, and a brief return note. No unnecessary sentences or fluff.

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 3 optional parameters and an output schema, the description covers parameter semantics and return type. However, it lacks explanation of what a 'span' is, how 'recent' is defined, and any behavioral context like sorted order or pagination behavior.

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?

While schema coverage is 0%, the description adds meaningful interpretations for all three parameters: session_id filters by session, run_id filters by run, limit sets max rows with default 50. This compensates for the lack of 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?

Description clearly states verb 'Fetch' and resource 'spans', with optional filters. It hints at recency but doesn't define it, and no explicit differentiation from sibling span tools like start_span or log_span, but the read intent is clear.

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?

No guidance on when to use this tool versus alternatives like get_agent_runs or other get_* tools. It mentions optional filters but doesn't specify scenarios where filtering by session vs run is appropriate.

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