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

Annotations declare the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds substantial operational context on top: a 32 KB payload cap, a 60 RPM rate limit, the '?demo=true' or L402 (30 sats) access path, and HTTP 400 on invalid input. That is exactly the kind of constraint detail annotations cannot carry.

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 purpose is front-loaded and every clause carries information (capabilities, triggers, alternative, constraints, error code). It is a dense semicolon-chained run-on, however, so the when-to-use versus when-not split reads less cleanly than it could.

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 values need no explanation, and annotations cover the safety profile. The description fills the remaining gaps — access modes, rate/size limits, failure behavior, and the sibling boundary — so an agent has everything needed to invoke it correctly.

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 100%, so the schema already documents all three parameters and their defaults, making 3 the baseline. The description only restates that segments_json is accepted 'with enum defaults', adding almost nothing beyond the 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?

Names three concrete operations (counting subword BPE tokens across segments, detecting instructions in the 35%–72% attention trough, computing USD/satoshi costs across frontier LLMs) with a clear verb+resource structure. It also explicitly distinguishes itself from the sibling prune_context_skeleton, so an agent can route 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?

Gives explicit when-to-use triggers ('auditing prompt token budgets, reordering prompt sections for primacy/recency attention, or comparing model API costs') and an explicit when-not with the named alternative ('for actively compressing and stripping low-salience lines from a single large file, use prune_context_skeleton instead'). No inference required.

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