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

With no annotations, the description carries the full burden and does: it discloses a quota cost ('Spends the plan's page allowance'), a destructive side effect ('replaces an exploration already running'), an async duration ('takes minutes'), and the return value (an exploration id). This is exactly the context annotations would otherwise have to supply.

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?

Four compact sentences, each carrying distinct information: purpose, sequencing, cost/side effect, and return/polling. The purpose leads and nothing is redundant with the schema or annotations.

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 supplies the return contract (exploration id) and the polling path (get_exploration, minutes). For a single-parameter async initiation tool, nothing an agent needs to call it correctly is missing.

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?

Only one parameter exists, and the schema documents it at 100% coverage ('The project whose app to explore'); the description's scoping language ('the project's app') reinforces the same meaning. A baseline of 3 would apply if this were a multi-param tool with full coverage, but with a single, fully described parameter the schema-plus-description pair leaves nothing ambiguous.

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 ('Explore the project's app') plus the outcome ('TestOptim learns new or changed pages and flows'), which distinguishes it from the read-only get_exploration sibling. An agent can tell immediately this is the initiation step, not a status check.

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?

Gives explicit timing ('after adding pages, before start_test_run') and names the follow-up tool ('poll get_exploration'). The only mild gap is no explicit 'do not use when' clause, but the sequencing and the note that it replaces a running exploration effectively covers the exclusion.

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