process_get

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. Beyond that the description discloses non-obvious behavior: truncation order (time, then lines, then bytes), half-open time ranges versus inclusive line ranges, the running-vs-completed meaning of 'last seconds', and that a byte cap can cut a line. That is substantive context annotations cannot carry, though interaction between simultaneous time and lines selectors is only hinted at.

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 core action, then defaults, then range semantics, then edge cases — a sensible order with no filler sentences. The opening phrase 'time, then lines, then UTF-8 text bytes' is terse to the point of being slightly cryptic about the precedence it is describing.

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?

An output schema exists, so return values need no explanation; the description instead spends its budget on the genuinely ambiguous parts (defaults, interval inclusivity, byte-budget truncation, absolute line numbering). For a read tool with rich annotations, nothing an agent needs in order to call it correctly is missing.

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?

With measured schema coverage at 0% for top-level properties, the description must compensate and largely does: it explains the units and interval semantics of the time selectors, the inclusivity of line ranges, and the truncation behavior of max_bytes. It adds nothing about process_id beyond the implicit 'process', so it falls short of fully covering every parameter.

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 opening clause 'Read a log slice' gives a specific verb and resource, and the description immediately bounds it to a single process's log stream, which cleanly separates it from siblings like processes_overview that enumerate processes. An agent can identify the operation without opening the 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?

It specifies the default behavior when no selector is given ('return the last 100 lines'), which is real usage guidance, but it never states when to prefer this tool over processes_overview or any other sibling, nor any prerequisites. Usage is implied by the selector semantics rather than stated.

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