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 explains what the response contains (default pick, strong alternatives and specialists, when to choose and avoid each, a scenario guide), the ranking criteria (code substance, engineering, real usage/downloads, maintenance rather than stars), and the fallback behavior. It omits any note on result caps or latency, but the substantive behavior is disclosed.

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?

The definition is a single front-loaded paragraph that opens with the verb and examples before moving to sourcing, ranking criteria, and fallback. It is dense but every sentence contributes; only the parenthetical example list runs slightly long.

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 must describe return values, and it does so in detail (default pick, alternatives, specialist picks, choose/avoid guidance, scenario guide). Combined with the ranking rationale and fallback, an agent has enough to decide and call it, with only minor gaps around result volume and comparison coverage.

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 input schema already documents need, limit, language and permissive_license, and the baseline is 3. The description adds a little by showing what a valid 'need' string looks like, but says nothing beyond the schema about how filters interact with the recommendation flow or whether a filtered need still returns comparisons.

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 gives a specific verb and resource ('Recommends open-source projects') plus three concrete example needs, and discloses the source of the recommendation ('Repolode's comparisons of similar projects'). It implicitly separates this from search_repos via the keyword-search fallback, but never explicitly contrasts itself with compare_projects or find_alternatives.

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?

Usage is implied by the example needs ('MCP server to query Postgres', 'self-hosted Google Photos replacement') and the note that it falls back to keyword search when no comparison exists, which tells an agent when it will still succeed. There is no explicit when-not guidance or statement of which sibling (compare_projects, find_alternatives, search_repos) to prefer in a given situation.

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