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

No annotations are present, so the description carries the full burden — and it delivers: active-only filtering, sort order (relevance then stars), nightly refresh from the public GitHub API, and match scope are all disclosed. This goes well beyond the schema and gives an agent accurate expectations for ordering, freshness, and what gets filtered out.

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 sentences of roughly 60 words, each carrying distinct information: search scope, result ordering, and invocation requirements plus data freshness. Content is front-loaded with the verb+resource, and there is zero redundancy with the schema.

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 a 5-parameter search tool, the description covers matching, filtering, ordering, freshness, and the required-input constraint, while the schema documents every parameter. The one gap is result shape: no output schema exists and the description never states what fields each result contains, so an agent cannot be certain results carry the identifier needed to chain to get_server.

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 covers all 5 parameters at 100%, so the baseline is 3. The description adds real value by stating the cross-parameter constraint (at least one of query/category/topic) and the interpretation of a missing query (category/topic enumeration by stars) — information that cannot be derived from any individual parameter's schema description.

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?

Opens with a specific verb+resource: 'Search the MCP server directory by keyword and/or filters.' It then pins down exact matching semantics (name, description, GitHub topics), which distinguishes it from siblings like get_server (single-server fetch), list_categories, and list_topics without needing to open their schemas.

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?

Provides explicit invocation guidance: 'Supply at least one of query, category, or topic,' and explains the zero-query path where filters alone enumerate a whole category or topic by stars. Parameter descriptions also cross-reference siblings (list_categories, list_topics), orienting the agent. It never explicitly states when not to use this tool versus get_server, so it just misses the top bar.

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