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

Beyond the readOnlyHint the description discloses a genuinely useful behavioral trait: a missing key returns `found: false` rather than raising an error, framed as a legitimate question. That is exactly the kind of context annotations don't carry. It remains silent on pagination and large-value behavior, which keeps it from a 5.

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 the verb and the two branches, then each branch explained in order. The closing analogy ('resume read of a piece of work') is a touch flowery, but it earns its place by encoding the index's purpose compactly.

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?

With no output schema, the description correctly carries the return-value burden, describing both response shapes (single value or `found: false`; or the index with keys, sizes, and dates). For a 2-parameter, all-optional read tool this is complete.

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 coverage is 100% and the schema's own `key` description already explains the omitted-key-becomes-index behavior, so the description largely restates what the schema provides. It adds the mental model of the index but no syntax or format details beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 (Reads) and resource (CUSTOM project metadata), and it crisply distinguishes the two operating modes: WITH key returns a value, WITHOUT key returns the index. An agent can tell this apart from set_project_metadata, delete_project_metadata, and update_meta without opening any 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?

The description explicitly tells the agent when each mode applies: use a key to fetch one value, omit it to survey the whole store via the index, with a clear rationale (cost of pouring a store into context). It stops short of naming alternative tools or exclusion conditions, so it is clear context without explicit alternatives.

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