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

With no annotations, the description carries the full burden and does real work: it discloses that every result reports commercial-use clearance, that results include a ready-made Markdown snippet with any required credit line, and that authenticated callers additionally receive their private library. It does not cover pagination, rate limits, or empty-result behavior, but the output-shape and auth-dependent behavior disclosures are substantive.

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?

Three dense sentences, front-loaded with the corpus scope before moving to query phrasing and output guarantees. Every clause carries information, though the parenthetical licensing details make it slightly heavy to scan.

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 an 8-parameter search tool with no output schema and no annotations, the description covers the corpus, query strategy, licensing metadata, credit-line behavior, and auth-gated private results. It omits return ordering/pagination and the meaning of kind values like 'upload' (left to the schema), leaving only minor gaps.

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 already 88%, so the baseline is 3, but the description adds genuine meaning: it explains the commercial_use distinction that drives commercial_only and no_credit, clarifies the private-library behavior behind private_only, and adds query semantics (language determines result language) that the schema does not encode.

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 verb (search) and a precisely bounded corpus: web-collected Chinese 表情包/斗图 and English reaction memes plus openly licensed emoji, art and photos. It also states the licensing split (commercial_use=false vs true) and language-dependent result behavior, which cleanly separates it from a direct-fetch sibling like get_meme.

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 actionable usage guidance ('search for the reaction you want in 1-3 words') and explains that Chinese queries surface Chinese 表情包 while English queries surface English memes, which shapes how an agent should phrase a call. It stops short of naming alternatives or stating when not to use this tool versus get_meme or list_categories.

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