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

Annotations only declare idempotency and non-destructiveness; the description adds substantive behavior the schema does not: unknown values are silently dropped, PII/free text is rejected, and profile scoping depends on whether a feed key is supplied. These are exactly the traits an agent needs before invoking a write.

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 field list comes first, then the safety constraint, then the consumer note, then the key semantics — a sensible front-loaded order. It is dense rather than padded, though the final sentence about feed keys is long enough to be easier as two clauses.

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 six-parameter write tool with no output schema and thin schema descriptions, the definition covers the privacy rules, value vocabularies, and key scoping well. It does not state whether a call replaces or merges with previously stored tags, which matters for a tool flagged idempotent.

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 only 17%, so the description must compensate and largely does: it restates the budget enum values, gives the allowed preference vocabulary (nocode|code|open-source|free-tier), clarifies that tools_in_use takes catalog ids, and explains the key's origin and effect. project_types and platforms are named but their value vocabularies are not described.

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 uses a specific verb pair ('Store ... as non-sensitive tags') and enumerates the exact fields written: project_types, platforms, budget, preferences, tools_in_use. It also explicitly states which downstream tool consumes the data ('Used by check_updates, not by recommend_tools'), so the agent knows what the resource is for.

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?

It gives a strong negative constraint ('never send names, emails, code, project names or free text') and explains when the optional key is needed versus falling back to the anonymous client identity. What it lacks is explicit when-to-call guidance relative to the sibling save_preferences, which is never mentioned.

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