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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so "Reads only their Achriom library" largely restates what structured data already says. The enumeration of returned values (counts, days-since-last-add, stage buckets) adds some useful context but shades into return-value documentation rather than behavioral disclosure; nothing is said about cost, caching, or failure modes for a sparse/empty library.

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?

A single front-loaded sentence that names the action, the target, the intended use, and the payload. The parenthetical stage enumeration is dense but each element is load-bearing since no output schema exists.

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 and no parameters, the description must explain what comes back, and it does: counts per media type, recency in days, a four-value stage classification, and taste signals. That is enough to call it correctly, though it leaves the agent unsure how this differs from get_stats or get_taste when choosing among siblings.

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?

The tool takes zero parameters, so the schema carries the full contract and there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly avoids inventing parameter guidance.

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 ("Summarise") and resource (the Achriom library) and enumerates what the summary contains: per-media-type counts, recency, a stage bucket, and taste signals. It is clear what the tool produces, but it does not distinguish itself from heavily overlapping siblings like get_stats, get_taste, get_taste_portrait, or get_signals, several of which sound like subsets of this output.

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?

"For pitching a conversation" gives a genuine usage context and implicitly suggests this is the lightweight pre-conversation overview. However, there is no explicit when-to-use versus get_stats (counts) or get_taste/get_taste_portrait (taste signals), so an agent must guess which of these overlapping read tools to pick.

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