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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description adds the parts annotations cannot: that it returns canonical IDs plus rich metadata, and that mood levels carry scope and evidence labels. The note that results may be viewer-mentioned titles or assistant-chosen mood references is genuinely useful behavioral context not present in any structured field.

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 sentences, front-loaded with the action, then the workflow constraint, then the return payload. The field enumeration in sentence two is dense but scannable and nothing is wasted on preamble.

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 single-parameter read-only resolver with an output schema present, the definition covers purpose, sequencing, and result shape. The one real omission is guidance on the kind/limit controls, which matter when a name is ambiguous between a movie and a series.

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 reported as 0% for a nested request object with four fields, yet the description only implicitly conveys query semantics (fragments and typos tolerated) and hints at exact-version resolution. It says nothing about kind, limit, or how year disambiguates a series' first-release year, leaving the agent dependent on the nested schema text.

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 a movie or TV show') and adds the crucial tolerance detail — name, remembered fragment, or typo — which tells an agent this is a fuzzy resolver, not a catalogue browser. It is clearly distinguishable from siblings like get_title_peers or recommend_titles.

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?

'Resolve its exact version before recommendations or availability checks' gives explicit ordering guidance relative to the recommendation and watch-option siblings. It does not name those siblings directly or state when not to use it, but the workflow placement is clear enough to route correctly.

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