prioritize_rice

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

With no annotations, the description carries the full burden, and it does disclose the key trait that this tool can mutate state when projectId is supplied. However it leaves the persistence semantics unexplained: whether saved items are appended or overwrite existing project items, whether validation failures on the numeric ranges abort the whole batch, and whether the save is reversible. Those are material gaps for a tool with a write path.

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 sentences, front-loaded with the core computation, with the conditional side effect second. Every clause earns its place and nothing is padded.

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 compute tool with no output schema and no annotations, the description should say what comes back — e.g. a sorted array with computed scores, and whether saved items return IDs. It also omits tie-breaking and handling of invalid inputs. Adequate to call the tool, but not complete.

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 coverage is only 50%, so the description needs to compensate, and it does meaningfully: it explains that projectId is not a filter but a persistence trigger, and the formula clarifies how reach/impact/confidence/effort combine into the output. It adds little about the item shape itself (names, ordering of results), but the numeric field meanings are already documented in the schema.

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 specific verb and resource ('Compute RICE scores ... for a list of ideas and sort them') and even supplies the formula (Reach × Impact × Confidence ÷ Effort), so the operation is unambiguous. The conditional side effect ('With projectId, saves the result to the project') further pins down what the call does; no sibling tool does scoring, so confusion is unlikely.

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 sentence 'With projectId, saves the result to the project' tells the agent about a mode switch, but it is phrased as behavior rather than guidance — it never says when to persist vs. compute-only, nor what prerequisites or consequences follow from saving. Usage is implied rather than stated, and no alternatives are named.

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