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

Annotations already cover read-only/idempotent/openWorld safety, yet the description adds substantial behavior: returns null when no saved analysis exists, analyses belong to the user rather than a brand, catalogSummary is returned independently in the brand language, and videos/transcripts are excluded. This is exactly the kind of context annotations cannot convey.

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 before the field list, and every clause on return shape earns its place since there is no output schema. However, it is one long run-on sentence whose density makes it slightly harder to parse than a few shorter sentences would 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?

With no output schema, the description compensates by enumerating the return object's fields, the null case, and the catalogSummary nuance. An agent calling this tool knows what it will and will not get back.

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 0%, so the description must carry the load. It clarifies creatorId's meaning and implies brandId matters ('catalogSummary in the brand language'), but never explains brandId directly or its role/behavior (e.g., whether it scopes anything else). Partial compensation only.

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?

Names a specific verb and resource ('Get the stored deep analysis of a creator by creatorId') and then enumerates the exact fields returned (positioning, pillars, targetAudience, tone, formats, hooks, whatToAdapt, funnel, videoType). The explicit exclusions ('does not return videos... and does not generate anything') separate it from run_creator_deep_analysis and the video tools.

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?

Usage is implied rather than stated: 'stored deep analysis' plus 'does not generate anything' hints that generation is a sibling's job, but no tool is named and no explicit when/when-not is given. The note about missing deep analysis vs. catalogSummary is helpful context but not routing guidance.

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