streaming_plan

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. The description adds real value beyond that: it discloses the analysis-only nature (no writes, proposals still required), the exclusion rule (punts excluded), and the shape of each returned move (effective ET day, expected cats gain, games added/lost, rest-of-season cost) — meaningful given there is no output schema.

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?

Purpose is front-loaded in the first sentence, followed by output detail, the one param clarification, and the analysis-only caveat. Three sentences with little waste, though the output-detail sentence is dense enough to be slightly hard to parse.

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 multi-move recommendation tool with no output schema and no annotations describing returns, the description does cover the return shape, which is the main gap-filler. It falls short on parameter explanations for three of four inputs, which is a notable omission for an optimization tool where 'adds' and 'drop_pool' drive the result.

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%, so the description must carry the burden, yet it only clarifies 'protect' (comma-separated names that must not be dropped). 'adds', 'opponent', and 'drop_pool' are entirely undocumented in both schema and description, leaving ambiguous semantics such as whether 'drop_pool' is a candidate count or a pool identifier.

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 names a specific output — a sequence of add/drop streaming moves optimizing expected categories won — which is far more precise than a generic 'plan' label. It implicitly distinguishes itself from execution siblings via 'Analysis only — moves still require proposals', though it never names the alternatives (evaluate_add_drop, waiver_decision) directly.

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 implied through scoping phrases like 'for the rest of this week within the remaining weekly adds' and 'punts excluded', which tell the agent the intended scenario. However, there is no explicit when-to-use-this-vs-evaluate_add_drop/waiver_decision guidance, leaving the agent to infer the boundary between this and its many siblings.

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