dev_search

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

With no annotations, the description carries the full burden and does so well: it discloses per-source isolation ('each source returns its own list'), graceful degradation ('a source that is rate limited reports an error without failing the call'), cost ($0.0045 USDC per call), and p99 latency (5000ms). These are exactly the traits an agent needs for planning and budgeting.

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?

Front-loaded with purpose, then sources, then failure semantics, then params, then cost/latency. Dense but nearly every clause earns its place; only minor tightening of the source list prose would help.

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 no-output-schema, no-annotation aggregation tool, the description covers params, per-source result shape ('its own list'), failure behavior, cost, and latency. Return-field granularity is not described, but that is largely outside a description's remit here.

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 0%, so the description must compensate, and it fully does: it names query as required, enumerates the sources default set, and gives limit's range (1-20) and default (5). Every parameter's meaning and defaults are recoverable from the text alone.

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 (Search) and resource (developer sources) and enumerates exactly which sources are queried: Hacker News, GitHub, npm, PyPI, Stack Overflow. This clearly distinguishes it from generic siblings like web_search, news_search, and discussion_search without opening a 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?

The phrase 'in one call' implies the aggregation value over single-source tools, and the PyPI note explains a source-specific limitation, but the description never states when to choose this over siblings such as web_search, package_check, or discussion_search, nor when to exclude a source. Usage is implied, not prescribed.

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