semantic_search

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

No annotations exist, so the description carries the full burden; it discloses the retrieval model and, importantly, the eventual-consistency caveat that new logs are only searchable after a background embedding job. It omits ordering/relevance scoring, result shape, and the fact that this is a read-only operation, which is a gap for a no-annotation tool but not a serious one.

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?

Three focused sentences: what it is, when to use it, and the freshness constraint. Front-loaded with purpose 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 3-param read tool with no output schema and no annotations, the description covers purpose, usage, and the main operational caveat (embedding lag). It stops short of describing result ordering or relevance scores, which an agent would want to know without an output schema.

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 100% (limit defaults/max, project_id guidance, query meaning all documented in the schema), so the baseline of 3 applies. The description adds only the semantic framing of 'query' as natural language, no new limit or project_id behavior.

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 (find log entries) plus the mechanism (vector similarity, explicitly 'not substring matching'), which distinguishes it from query_logs/query_logs_batched without naming them. The example query makes the semantics concrete.

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 an explicit when-to-use rule (user describes a problem in their own words rather than citing exact log text) with an illustrative example. It implies but never names the alternative tool to use for exact-text lookups, so routing is left slightly to inference.

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