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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses that this writes to the user's Lab, that a human confirmation gate precedes the call, that the server validates the spec and returns a refusal reason, and that POLYRANK_API_KEY is required. These are exactly the operational facts an agent needs before mutating user state.

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 critical guardrail (ask the user, pass confirm: true) is front-loaded in the first sentence and nothing is padded with filler. There is minor redundancy in restating the 'Lab' framing twice across the first two sentences, but the density is justified by the amount of behavior conveyed.

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 nested-object mutation tool with no output schema, the description covers validation failure behavior and the auth requirement, which are the highest-risk unknowns. It does not say what a successful response contains (e.g. a new strategy id the agent would need for polyrank_get_strategy or polyrank_run_backtest), which is the one remaining gap.

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% and 'name' and 'template_id' carry no schema description, but the description compensates by explaining that 'name' is paired with a spec, that template_id is a mutually-exclusive copy path, and by unpacking spec into wallet source (Builder ranking, history ranking, static list, copy-engine sleeve) plus market, entry, sizing and exit rules. That is real meaning beyond the schema's bare 'see polyrank_list_lab_templates' pointer.

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: 'Save a strategy to your Lab', and enumerates what is being saved (a name plus a spec, or a template_id copy). It is clear this creates a new strategy rather than modifying one, though it never names polyrank_update_strategy or polyrank_list_strategies to make that contrast explicit.

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?

It gives a concrete precondition ('ask the user before calling, then pass confirm: true') and presents the two divergent invocation paths: a full spec versus a template_id copy. What is missing is an explicit when-not case, e.g. when to call polyrank_update_strategy instead of creating a new strategy.

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