Search Savvly Q&A Content Library

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds meaningful behavioral context: entries carry 'verbatim answer plus any disclaimer footnotes,' and responses include 'primary sources (e.g. SEC filings)' for reference. This goes beyond annotations by describing data provenance and content structure. No contradiction with annotations.

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 description is well-structured, front-loading the core purpose and use case, then adding content details and source attribution. Each sentence contributes value: purpose, when-to-use, data characteristics, and provenance. It is somewhat lengthy but not redundant. A slightly tighter version could condense the examples, but overall it's efficient and organized.

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?

Given the existence of an output schema (noted in context signals), the description does not need to explain return values. Annotations cover safety, and the description provides comprehensive context: what the library contains, how it's organized, when to use it, and what each entry includes (verbatim answers, footnotes, primary sources). For a read-only search tool with four optional parameters, nothing essential is missing for correct invocation.

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 description coverage is 100% (all four parameters have descriptions), baseline 3. The description adds value by specifying multi-word query behavior ('match entries containing ANY of the words, ranked by relevance') and provides concrete examples for section slugs ('tax-legacy', 'retention-talent-strategy') and clarifies audience semantics ('general' is the factual FAQ). It also notes substring matching for section. These details enhance the schema's minimal descriptions.

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 clearly states the verb (search), the resource (Savvly Q&A Content Library), and the content type (audience-tagged questions and answers). It differentiates from siblings by specifying the use case: 'positioning, value props, audience-specific talking points, or Q&A-style messaging,' which distinguishes it from get_savvly_faq (likely a static FAQ) and other tools. The organization by stakeholder and section is also included, making the purpose unambiguous.

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?

The description explicitly says 'Use this when the user asks about Savvly's positioning...' providing clear when-to-use guidance. However, it does not explicitly mention when NOT to use it or name specific alternatives, though the sibling list and context imply get_savvly_faq might serve the full FAQ. It also clarifies the 'general' audience as the factual FAQ, giving additional contextual direction. Lacks explicit exclusions but is still strong.

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