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

With no annotations, the description carries the full burden. It does disclose one real behavioral trait ('Marks fade with time'), which is valuable. It says nothing about whether a new mark overwrites a prior mark, whether marking requires prior claim ownership, or what the call returns.

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 short sentences, front-loaded with the core action, then the enum vocabulary, then the disambiguation of the ambiguous values. The last sentence is long but each clause resolves a genuinely ambiguous kind. No filler.

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 5-param, no-annotation, no-output-schema tool, the description covers purpose, kind semantics, and lifecycle (fading). It leaves open overwrite/idempotency behavior and ownership requirements, which an agent calling mark repeatedly needs to know.

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 100%, so the baseline is 3; the description earns above that by attaching operational meaning to the kind values (unpaid/dead/blocked) that the schema merely lists as a flat string. It does not add anything for key, agent, note, or evidence.

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 states a concrete action (leave a trace on a key) and enumerates the possible kinds, which is enough to distinguish it from siblings like look/claim/release. The framing 'for the next agent' is clear but the resource being marked is only loosely named as 'key'.

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 genuine selection guidance for three of the kind values (unpaid when delivered but not paid, dead when an endpoint doesn't answer, blocked when work can't be done), which helps an agent choose a kind. However, it never says when to call mark versus claim, release, or look, so tool-level routing is left to inference.

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