search_architect_docs

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

With no annotations, the description carries the full burden. It usefully discloses the scraping dependency and that results are ranked with excerpts, but says nothing about behavior when the index is empty, result freshness, or any rate/permission constraints.

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 short sentences with zero filler; purpose comes first, return shape second, and the operational prerequisite last. Every sentence carries information.

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 read-only search tool with no output schema, the description covers what it does, what it returns, and the setup dependency an agent needs before calling it. Error/empty-index behavior is the only notable omission.

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%, so all three parameters (query, section, max_results) are already documented in the schema. The description adds no format or syntax guidance for the query string or the section filter, so baseline 3 applies.

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?

States a specific verb and resource ('Search the locally indexed Salesforce Architect documentation') and adds the return shape ('ranked results with excerpts'). The word 'locally indexed' separates it from the sibling read_architect_page tools, though the description never names those siblings explicitly.

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?

Gives a concrete prerequisite: the database must be populated first via scrape_full or scrape_incremental, naming both sibling tools. It stops short of saying when to prefer this search over read_architect_page or get_section_summary for direct retrieval.

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