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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered by structured data. The description adds genuinely non-derivable behavior: 'No model is consulted' (the answer is computed, not generated) and 'nothing is reserved for you' (the agent must claim the slice itself). It stops short of stating freshness, rate limits, or failure behavior.

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 core action is front-loaded in the first sentence and the follow-up step is placed at the end where it is easy to act on. The middle sentence is long and packed with clauses, but each clause (arithmetic, alternatives, call sequence) conveys distinct return information rather than 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?

There is no output schema, so the description must describe the return, and it does: the recommended work, the supporting arithmetic, the alternatives, and the exact call sequence. Combined with the explicit non-reservation caveat and the next-step pointer, this is close to complete for a 3-optional-param read tool.

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% for all three optional parameters (kind/level/effort), so the schema already carries the semantics. The description never references these filters, adding no meaning beyond what the schema provides, which is the baseline 3 when schema does the heavy lifting.

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?

States a concrete verb+resource: it returns the single best piece of standing research to do next, along with the arithmetic, alternatives, and the call sequence. That is far more specific than a tautology. It does not, however, contrast itself with adjacent tools that also surface 'what to work on' (e.g. get_open_questions, list_dead_ends), so sibling differentiation is only partial.

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 opening imperative 'ASK WHAT TO DO NEXT' plus the trailing 'NEXT: claim_work' gives a clear use context and a concrete follow-up workflow. What is missing is any exclusion or comparison to alternatives for deciding work, so an agent isn't told when NOT to use this tool.

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