ContextFetch deep research

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses credit cost per sub-query (1 credit each), server-side execution, deduping/ranking behavior, and the exact derivation logic used when sub_queries is omitted. This is substantial behavioral context the annotations cannot convey.

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?

A single dense paragraph that front-loads the alias note and output shape before the parameter-usage guidance. Every clause carries information, though the fallback-derivation sentence is long and slightly nested.

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?

With no output schema, the description fully specifies the return artifact (one Markdown evidence pack, numbered sources, pruned passages) plus cost and query-derivation rules. An agent has everything needed to invoke it correctly.

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 already 100%, so the baseline is 3. The description goes beyond it by explaining how sub_queries is synthesized (query itself, + 'documentation', + 'benchmark' or 'example' with suffix-skip rules) and by tying sub-query count to credit consumption, adding real semantic value.

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 precisely what the tool produces: a single Markdown evidence pack with numbered sources and query-pruned passages, built from up to 3 server-side sub-queries. It also positions itself relative to a sibling by declaring it is an alias of contextfetch_research kept for existing setups.

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 strong explicit recommendation ('You SHOULD pass your own sub_queries... for better coverage') and explains the fallback when omitted. It does not, however, tell the agent when to prefer this over contextfetch_research, contextfetch_search or contextfetch_answer, so the alternative-selection guidance is only partial.

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