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

Annotations already cover readOnly/idempotent/non-destructive, so the safety profile is given. The description adds genuinely useful context beyond that: the required scope (tickets:read) and, most importantly, pagination behavior ('Page history with next_before_revision while has_more'). 'No state changes' largely restates readOnlyHint, which slightly dilutes the value.

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 tight sentences, front-loaded with the core read purpose, then the archived-project caveat, then the pagination/permission mechanics. No filler, though the naming of return fields (next_before_revision, has_more) is dense shorthand that only pays off if the agent already knows the API.

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 three-parameter read tool with no output schema, the description usefully names the two response fields driving pagination (next_before_revision, has_more), covering return-value behavior that no structured field provides. Annotations cover the mutation/idempotency profile. The only real gap is the semantics of the limit and before_revision inputs.

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 0% and all three parameters are undocumented in the schema, so the description must carry the load. It implies project_id ('one owned project') and describes history paging via next_before_revision/has_more, but those names look like response fields rather than the actual inputs: the `limit` and `before_revision` input parameters are never explained (bounds, direction, relationship). Compensation is only partial for a 0%-coverage 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 (Read) and a precise resource: one owned project's current override/inherited owner policy, effective policy, and immutable project history. The word 'project' distinguishes it from the sibling get_ticket_attention_policy, and 'current/effective' versus 'immutable history' clarifies the two data facets it returns. It stops short of explicitly naming the alternative tools it is not.

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?

'Read one owned project's ...' and 'Archived projects retain authority' give implicit conditions for when this applies, and 'Requires tickets:read' states a prerequisite. However, it never names an alternative (e.g., get_ticket_attention_policy, save_project_attention_policy) or states when-not to use it, so the agent must infer routing from the tool name alone.

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