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

Beyond destructiveHint=true and openWorldHint=true, the description discloses the exposure scope ('readable by anyone at its link', 'showing its images, not its scene', 'revokes them all') and that data leaves the system to Zindex support/staff. It also flags the confirmation gate for four actions, which the annotations do not convey. It doesn't state reversibility of unpublish or what the confirm token flow 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?

Compact and action-ordered, front-loading the four sharing verbs before the two support verbs, with zero filler. The semicolon-chained clauses are dense enough that a fast reader may mis-parse where one action's semantics end and the next begins.

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 12-parameter destructive multi-action tool with no output schema, the description covers the actions and confirmation gate but leaves the feedback/report payload fields (expected, observed, confidence, anonymize) and the confirm token mechanics unexplained. An agent could pick the right action but would still guess at how to fill several parameters.

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?

At 58% schema coverage, the description compensates for some gaps: it explains the 'docs' kind meaning, that id or snippet attaches a diagram, and that report targets one version (implying revision). It says nothing about expected, observed, confidence, or anonymize, leaving several maxLength-bounded fields undocumented in both places.

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?

Each of the six actions is given a specific verb+effect (publish makes readable at its link, unlink revokes all links, report sends one version to support), so an agent knows exactly what this tool does per action. It does not differentiate the tool from siblings like diagram_get or diagram_render, which would require a single framing sentence about sharing vs. reading.

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?

The per-action semantics effectively encode when to choose each action, and the closing sentence names which actions trigger a user confirmation (publish, link, report, feedback), which is real selection guidance. It stops short of explicit exclusions or cross-references to alternatives such as diagram_history for version inspection.

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