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

Annotations already declare readOnlyHint and openWorldHint, so the description adds meaningful extra context: cost (one embed + one vector search), network direction (outbound to embed model only), return behavior (ranked snippets with source URLs), and an instruction to cite source_url verbatim. It also warns that the corpus has current text that training data may not, adding important reliability context.

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 long but every sentence is information-dense. It is front-loaded with a cost/network/read-only summary, then organized into corpus scope, trigger conditions, return behavior, examples, and tool-pairing guidance. The structure makes the length justified for a tool with many trigger categories and no 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?

For a RAG search tool with no output schema, the description fully covers what is searched, when to use it, what it returns, and how to cite sources. It also references alternative tools and the optional vendor filter, leaving no obvious gaps for an agent to misuse the tool.

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 the description doesn't need to restate parameter meanings. It adds only mild context, such as using detect_sip_stack to derive the vendor filter and illustrating query specificity with examples, but the schema already instructs users to include vendor/header/code/RFC. Baseline 3 is appropriate because the schema carries the semantic load.

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 'Vector search over Sipflow's curated VoIP knowledge base' and enumerates the corpus (vendor docs, RFCs, STIR/SHAKEN, branded-calling, fax-over-IP). It clearly distinguishes this RAG search from sibling lookup tools by stating 'USE FIRST whenever the user asks about - or attaches - anything SIP/VoIP/telecom shaped' and naming alternatives in the Pair-with line.

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 gives explicit 'USE FIRST whenever' guidance plus extensive trigger conditions: vendor configs, dialplan/routing scripts, SIP headers, response codes, RFC questions, captured traces, STIR/SHAKEN, and T.38 fax issues. It also provides 13 concrete examples and explicitly says to pair with detect_sip_stack, lookup_response_code/lookup_sip_header to short-circuit, and troubleshoot_response_code for status-code-rooted questions, covering when-not-to-use.

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