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

With no annotations, the description carries the full burden and does well: it discloses the underlying dataset and size (NEAR Catalog, 340), the fields returned, and edge-case behavior (empty query returns top-TVL projects; unknown category returns the category list). It omits anything about ranking for text queries, pagination beyond limit, or error/permission behavior, which keeps it short of a 5.

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?

Purpose and scope are front-loaded, followed by returnable facets, then behavioral edge cases, then example prompts. The middle facet list is dense and slightly enumerative, but every element maps to something an agent needs to judge relevance; nothing is filler.

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 listing the per-project fields an agent will get back, plus default-limit behavior (5, up to 50 for a full category). It is near-complete for a 3-parameter read tool, with only result ordering for text queries and truncation behavior left unaddressed.

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%, so the baseline is 3, but the description adds real meaning: it explains that an empty query is a listing mode ordered by TVL, that category alone can enumerate a whole vertical ('Wallet', 'DEX', 'Validator'), and that query accepts natural-language descriptions of what a project does. That goes beyond the schema's terse field notes and helps the agent choose parameter combinations.

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 with a specific verb and resource ('Find NEAR ecosystem projects in NEAR Catalog (340)') and immediately scopes what can be searched (name, function, category). It enumerates the returned facets (category, phase, website, GitHub, tokens with NEAR contract, TVL, security incidents, partner status), which clearly separates it from generic siblings like search or semantic_search.

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?

Concrete trigger examples ('what is Rhea Finance', 'which wallets can I use on NEAR', 'has Meta Pool been hacked') and the empty-query / whole-category behavior give clear guidance on when to reach for this tool. It never explicitly names a sibling such as search or get_contract_info as the alternative, so the routing to other tools is left implicit.

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