snapshot_object

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

With annotations present, the description still adds substantial non-obvious behavior: the store is a process-lifetime map, persist=true writes Saved/MCPAudits/snapshots/<handle>.json and survives an editor restart, an existing handle is overwritten, and return_snapshot lets the caller hold the data for a later diff. The one soft spot is the "(read-only)" label, which could be misread as a tool-level safety claim even though the annotations mark the tool destructive and the text itself discloses file writes and overwrites.

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?

Front-loaded with purpose and usage in the first clause, followed by the persist caveat and the sibling exclusion. The dense "Returns:" enumeration is long but earns its place because no output schema exists; otherwise the wording is tight and waste-free.

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?

Covers what is captured, the two storage modes, the alternative tool, and enumerates the return fields in lieu of an output schema, which is appropriate for a 7-parameter, world-aware tool. Only ambiguity is whether the "(read-only)" qualifier versus the destructive annotation could steer an agent wrong.

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% (7 params), so the schema already documents world selectors, persist, handle/snapshot_id aliasing, return_snapshot, and include_component_templates with the same rationale. The description largely restates that material, so baseline 3 is appropriate; its added value (the workflow link between return_snapshot and diff_object_snapshots' snapshot_a/snapshot_b) belongs more to usage than to parameter semantics.

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 and resource ("Capture the properties and components of one object into a named in-memory snapshot") plus the downstream purpose (a later diff_object_snapshots). It explicitly differentiates from the closest sibling with "compare_objects diffs two live objects instead." An agent can tell this apart from compare_objects/diff_object_snapshots without opening a 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 concrete usage scenarios ("before vs after an action, editor vs PIE, or 'server' vs 'client' via world") and names the alternative route (compare_objects for two live objects). The when-to-use and when-to-use-something-else conditions are both present and explicit.

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