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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), so the remaining burden is output semantics — and the description does add real value there: relevance scores on roughly a 0–1 scale, best-first ordering, and a 0.1 unrelated threshold. What it omits is the practical side of the tool: whether search is exhaustive, how the index is maintained, or what happens with a 500-char query, though the score calibration note partially compensates.

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 core guidance is front-loaded and every clause is functional, but the opening sentence is a run-on whose illustrative rider ('cutting the pauses, ums and restarts out of a talking video, for one') reads as filler. The score-calibration sentence is long and comma-chained, making the thresholds harder to scan than they need to be.

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?

An output schema exists, so return-shape explanation is rightly omitted, and the description covers the one thing the schema can't: how to interpret the relevance score and what to do next. The only gap is that it never tells the agent when to raise or lower the limit, which is the sole non-obvious parameter choice left.

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% and both parameter descriptions already state 'in their words' phrasing and 'most matches to return, best first', so the description largely restates the schema. It adds no format, syntax, or limit-tuning guidance beyond what the schema provides; baseline 3 applies.

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 concrete verb and resource ('Find step-by-step instructions for a common job') and anchors it with a concrete worked example (removing ums/pauses from a talking video). It also implicitly separates itself from skills.get, which it names as the follow-up read step, so an agent can tell search from fetch without opening either 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?

Explicitly says to search in the user's words and prescribes the full workflow: search, triage results by score, read candidates with skills.get, then follow the skill's Steps. It even warns against a specific failure mode (keyword-sharing false positives scoring as high as real fits), which is genuine when/when-not guidance.

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