read_evidence

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

Annotations declare readOnlyHint=true, yet the description states 'Each call appends metadata-only receipt lines ... to ComplyEaze Bridge's local log on this computer' — a side-effecting write to the local environment, which contradicts a read-only hint (and is consistent with idempotentHint=false). The description is otherwise unusually rich (egress disclosure, masking limits, in-memory bounding), but the stated write side effect directly conflicts with the annotation.

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?

The content is dense and every sentence is relevant, but it is not front-loaded: the opening sentence is a privacy caveat rather than the tool's purpose, and the actual 'Shows ... recent reads' statement is buried mid-paragraph. For a one-parameter tool the ~120 words could be ordered far better.

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 one optional param, no output schema, and annotations present, the description covers what is returned (fingerprints, byte counts, state, no figures/book content), the memory-bounded window, and side effects. The main omissions are the default limit value and the readOnlyHint conflict, but an agent has enough to call it correctly.

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 the parameter. It does explain the sole parameter: the result is 'bounded: the newest `limit` records,' clarifying that limit selects the newest N records. It omits the default (20) and any upper bound, but the core semantic is supplied.

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?

The description states a specific verb+resource: it 'Shows ComplyEaze Bridge's own recent reads since it started,' including 'request and response fingerprints, byte counts and state.' That is a concrete, distinguishable purpose. However, it never explicitly names the siblings it differs from (e.g. egress_log, local_data_report), so it stops short of full sibling differentiation.

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/when-not guidance. The only directive ('Never tell the user that no data has left their computer') is a behavioral prohibition, not a usage rule, and there is no indication of when an agent should call this instead of egress_log or local_data_report. Usage must be inferred from the content of what it returns.

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