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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral value by declaring a precedence rule when both parameters are supplied and by qualifying ownership ("owned project") versus tracked-brand membership, which is not derivable from structured fields.

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?

Two sentences, zero filler, and the core action is front-loaded ahead of parameter routing. The second sentence is dense with domain terms ("memberships," "actively tracked internal brand record") that could be unpacked slightly, but nothing is wasted.

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 two-optional-parameter read with no output schema and no required inputs, the description covers parameter behavior adequately. What is missing is any sense of what a "project" record contains or how results are shaped/ordered, which the agent cannot infer from an absent output schema.

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%, so the description must carry both parameters, and it does: public_id returns a single owned project, brand_id returns memberships tied to an actively tracked internal brand record. The precedence rule resolves the ambiguous case. It stops short of giving ID formats or result shape, keeping it from a 5.

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 plus resource ("Read your projects") and immediately clarifies the two selection modes, so the agent knows this is a scoped read. It does not distinguish itself from siblings such as list_tracked_brands or search_tracked_brands, and "projects" is left undefined for an unfamiliar agent.

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?

Usage is implied rather than stated: the two clauses effectively say "use public_id for one owned project, brand_id for tracked-brand memberships," which is a form of routing. But there is no explicit when-to-use vs. when-not, and no mention of the sibling tools that surface advertiser/brand data.

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