read_log

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

Beyond the annotations (readOnly/idempotent/non-destructive already cover safety), the description adds real operational context: request bounds (seven, or ten without `kind`), line limits (default 100, max 500), the one-mebibyte read window, the 65536-byte JSON cap, and truncation signaling. It also carries a prompt-injection warning that `untrusted_lines` are third-party output to be treated as data, which the annotations cannot convey.

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 but front-loaded with the core purpose, then organized into clear Return, Touch, and Bounds blocks. Every clause carries information, though the prose is wordier than strictly necessary for the bounds figures.

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 filtered-read tool with 6 params, 0% schema coverage, and an output schema, the description fills every gap an agent needs: default log selection, filtering semantics, hard limits, truncation, and the security caveat on returned lines. Nothing required 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?

Schema description coverage is 0%, so the description must compensate, and it does for the non-obvious parameters: `kind` defaults to install/odoo, `contains` matches literally rather than as a pattern, and `lines` defaults to 100 with a 500 cap. `project`, `branch`, and `build_id` semantics are largely self-evident and only lightly addressed.

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 and resource ('Read the last lines of a log of a build of a branch of a project') and immediately scopes it to a specific build number or the latest. It also defines the default log selection (install if present, otherwise odoo) and the `contains` filter, so an agent can distinguish this read tool from `get_build` and `wait_for_build` 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 clearly explains selection conditions: without `kind` you get install-then-odoo, `build_id` selects a specific build versus latest, and `contains` filters literally (explicitly not a pattern). No sibling is named as an alternative, which keeps it from a 5, but usage conditions are otherwise explicit.

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