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

With no annotations, the description carries the full burden and delivers: HTML/entity/redirector stripping for AMO vs pass-through for Chrome, the Chrome-vs-Firefox locale rendering difference ('real, not a bug'), the copy-timeline side effect of signed-in reads, guest reads writing no research state, day-long caching with 'pending' cold-start, and 'sign_in_required' for uncached guest reads. This is exactly the behavioral depth an agent needs.

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?

Front-loads purpose and function, then layers behavior in short paragraphs. Mostly tight, but 'tracked by any account, not just yours' is repeated (once in include_copy_history's schema text), and the block is longer than strictly necessary, costing a perfect score.

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?

No output schema exists, yet the description enumerates the returned fields (description, supported languages, category, install count, rating, version) and covers all three terminal states (pending, ready, sign_in_required) plus cache-age behavior. An agent has everything needed to poll and interpret results.

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 80%, so the baseline is 3; the description adds value by explaining that locale changes which store language is used and how the store renders languages, and by describing include_copy_history's scope (only stored listings, signed in only). It doesn't restate external_id formats or max_age beyond the schema, but the added locale/copy-history context lifts it above baseline.

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 (return one extension's store page) and resource, with the key scoping fact up front: 'any extension, tracked by this account or not.' This immediately distinguishes it from get_extension, which is for tracked extensions.

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?

Explicitly positions itself as 'the competitor-research and copy-review tool' and names the alternative and its condition: 'Use get_extension instead ... when you want its recorded numbers over time.' Both when-to-use and when-to-use-something-else are covered.

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