search_all

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

With no annotations, the description carries the full burden. It does add genuine behavioral context — 14+ sources, embedding dedup, reranking — but says nothing about cost/latency of fanning out to all sources, per-source failure behavior, result ordering, or that synthesis silently no-ops without GROQ keys (that only appears in the schema). Adequate, with real gaps for a 12-parameter fan-out tool.

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?

Two front-loaded sentences plus a compact example; the routing guidance precedes the example and nothing is redundant. Every element earns its place.

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?

Routing is complete, but for a 12-parameter tool with no annotations and no output schema the description leaves the result shape unexplained (merged ranked list vs. per-source groups) and does not cover parameter interplay. Enough to call it, not enough to call it correctly in every case.

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 only 50% across 12 parameters, so the description must compensate and largely does not. The lone example only exercises query and language; it never clarifies how repo/owner, library/version, fromdate/todate (Stack Exchange-only), or fields_of_study map to particular sources, which is the main source of misuse risk.

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 ('Unified search across 14+ sources') plus the differentiating mechanism (embedding dedup and reranking). It explicitly distinguishes itself from the single-source siblings so_search/hn/papers/code_search, so an agent can pick it without opening any schema.

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?

Names the selection rule directly: use this for 'broad multi-source discovery', use the single-source tools for 'surgical single-source work'. That is an explicit when/when-not plus named alternatives, and the inline example reinforces the intended shape of a call.

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