Competitor teardown

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

The description discloses credit costs ('spends credits, free when you pass ads'), the conditional data source (auto-pulls Meta ads when `ads` omitted), and that it auto-tailors outputs to the saved brand. These go beyond the annotations (readOnlyHint, destructiveHint) which only cover safety. No contradiction; the tool is read-only yet consumes credits, and this is clearly stated.

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 description is lengthy but every sentence carries operational information: outputs in caps, the contract, the credit behavior, and auto-tailoring. It front-loads the core purpose and uses structural markers (CONTRACT) for clarity. Minor redundancy (spending mention twice) but nothing trivial. Efficiency is high given the tool's complexity.

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 tool with no output schema and only safety annotations, the description is remarkably complete. It specifies inputs, the conditional behavior, cost implications, and the nature of outputs (playbook components). The only missing piece is exact output format, but the enumerated deliverables suffice for an agent to know what to expect.

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 100% with descriptions for all three parameters. The description enriches meaning: for `ads`, it explains the two modes (supply or omit) and the consequence of omission; for `competitor`, it adds that domain sharpens page match. This adds contract-level semantics not present in the field descriptions, justifying above the baseline of 3.

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 opens by stating a specific verb-resource pair ('Tear a competitor's ad strategy down into an actionable playbook') and enumerates concrete outputs (opening-hook MIX, longest-running THEMES, WHITE SPACE, COUNTER-PLAYS). It clearly distinguishes itself from sibling research tools like research_ads or search_meta_ads by focusing on a strategic teardown rather than raw data retrieval.

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 'CONTRACT' section explicitly tells an agent when to pass `ads` (after a pull_competitor_ads / search_meta_ads call) versus when to omit it (auto-pull, spending credits). It implies the tool is for creating a playbook, contrasting with pure research tools. It could name alternatives more explicitly, but the usage context is clear enough.

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