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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior. The description adds two useful behavioral facts — that the sync is 'bounded' and that the changeNarrative must be hand-written rather than generated — but says nothing about locking, resumability, partial-failure behavior, or what a successful begin 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?

A single sentence with no filler, and the most important scoping information (bounded graph sync) is front-loaded. 'Bounded' is doing a lot of unexplained work for one word, but the sentence itself is efficient.

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?

Twelve parameters, nine required, a nested object, no output schema, and a 42% coverage schema, yet the description does not explain the declared* size declarations, the concurrency role of expectedProjectVersion, or the sync lifecycle (status polling via get_project_sync_status, abort_project_sync on failure). For a protocol-entry mutation this leaves substantial gaps.

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 only 42% across 12 parameters, so the description should compensate more than it does. It does clarify the semantics of changeNarrative ('four plain-language sections written manually'), which maps to the nested object, but the four declared* count parameters, sessionId/executionId, and mappedRevision remain unexplained beyond the schema.

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 (Begin) and resource (hosted graph synchronization) and adds the key constraint that it is bounded and that changeNarrative is supplied by the publishing agent. It does not name the sibling flow steps (append_project_sync_chunk, commit_project_sync, seal_project_sync), so the agent must infer this is the entry point of a multi-call protocol.

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?

There is no explicit when-to-use or when-not guidance, and no mention of the alternative tools (graph_sync, publish_project_graph, patch_project_graph) or of the required follow-up calls. 'Begin' implies a first step, but the description never says what to do next or under what circumstances this path should be chosen over a one-shot publish.

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