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

With no annotations, the description must carry the behavioral burden, and it does disclose two useful traits: runs are long-lived (minutes, implying repeated polling) and results are informational rather than actionable. It omits failure behavior for unknown run_ids and any indication of what the returned progress fields contain.

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?

Two short sentences with the primary scope constraint front-loaded and no filler. The trailing clause about results being informational is slightly vague but still carries signal, so it earns its place.

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 two-parameter getter with no output schema and no annotations, the description should say more about the returned progress object, such as status values or completion indicators. It is adequate but leaves the agent guessing about what to inspect while polling.

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 100%, so both run_id and organisation are already well documented in the schema, including the OAuth/API-key scoping nuance. The description adds no further meaning about run_id, so the baseline of 3 applies.

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 and resource ("Returns one eval run and its progress") and carves out scope with "without the task rows", which separates it from a fuller retrieval. It does not name a sibling such as start_eval_run or export_eval to sharpen the distinction, so it stops short of a 5.

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 only implied: the "without the task rows" clause suggests a heavier variant exists, and "eval runs take minutes" hints at polling for status. There is no explicit statement of when to call this versus start_eval_run or export_eval, and no stated preconditions.

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