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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it states the call is project-scoped (acts only on explicit project_id), returns duration and license terms, and instructs the agent to relay license terms. It also discloses the default max_seconds behavior. This is strong added value, though it doesn't describe pagination or result count limits.

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 dense but well-organized, with the project-scoping constraint front-loaded and the query-format guidance following. Every sentence earns its place, though the parenthetical list of examples and the license-term instruction make it slightly long. It is appropriately sized for the complexity of the tool.

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 the key operational details: what to search, how to phrase the query, the project scope, the max_seconds behavior, and the license-term relay requirement. It doesn't describe result count limits or pagination, but those are minor gaps given the tool's simplicity and the annotations' safety coverage.

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 only 33%, so the description carries significant weight. It explains the query parameter semantics (physical sound name, not mood), clarifies max_seconds (caps length, default 15s, one-shots are seconds long), and emphasizes project_id as an immutable scope. This compensates well for the sparse schema, though it doesn't enumerate every possible query format.

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 states a specific verb ('Search') and resource ('web for a REAL recorded sound effect'), and explicitly scopes the call to a project_id. It distinguishes itself from siblings like add_sfx, add_web_sfx, fetch_sfx, and audition_sfx_candidates by emphasizing web search for real recorded sounds by physical name, not mood. The instruction to query by physical name ('whoosh', 'camera shutter') is a clear, differentiating behavioral rule.

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 when-to-use guidance: use this when searching the web for a real recorded sound effect, and it tells the agent what to query by (physical name, not mood). It also names the alternative path implicitly by contrasting with mood-based search and by noting the project-scoped nature. The max_seconds cap and license-term relay instruction provide additional usage context.

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