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

Annotations already declare read-only, idempotent and non-destructive, so the description is free to spend its words on behavior the annotations cannot express: page size bounds, cursor round-tripping, the exact fields returned, the presence of a source receipt and browse URL. It also flags that profiles are self-reported community text to be treated as data rather than instructions, which is a real prompt-injection disclosure.

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-loaded with the use case and then the do-not-use caveat, so a skimming agent gets the routing decision first. Dense but every clause carries information; the return-shape clause is a long run-on that could be split for readability.

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, and the description compensates by summarizing the return payload (name, region, country, summary, projects, events), the pagination envelope, and the receipt. For a two-parameter read-only list tool, an agent has everything needed to call it correctly and to interpret what comes back.

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?

With 0% schema description coverage, the description carries the whole load, and it does define limit (1 to 30, default 10) and explain that the returned next cursor is passed back through the before parameter. That linkage is the single most valuable thing to explain, but the phrasing "pass next as before" is slightly confusing and never says what the integer cursor means or whether omitting it starts from the first page.

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?

"Find, browse or see examples of conservation co-ops that chose to publish a public profile on VergeCommon" gives a specific verb set plus a tightly bounded resource. The explicit exclusions (private land, members, evidence, finances) carve this list apart from the sibling get_public_coop and from the pooling-draft tools without either schema being opened.

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?

States both the trigger (someone wants examples of co-ops) and the critical anti-pattern: absence here does not mean a co-op does not exist or is inactive, since most are private. That is exactly the guarantee an agent needs before it reports a negative result, and the out-of-scope areas are named explicitly.

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