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

Annotations only declare readOnlyHint=true, so the description carries most of the behavioral burden. It adds meaningful context: call exactly once, prefer whats_new for repeated visits, and depth controls whether output is summarized or verbatim. Nothing contradicts the read-only 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?

Three compact sentences deliver the resource description, usage rule, alternative, and parameter semantics with no filler. The most important usage guidance ('call once') is front-loaded, and each clause earns its place.

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 the description does not need to enumerate return values. It provides the trigger condition, the cheaper alternative, and depth semantics, which is enough for an agent to select and invoke the tool correctly. The only lightly covered parameter, project_id, is clear from its name and required status.

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. It fully explains depth with its default ('brief') and alternative value ('full'), but it says nothing about project_id beyond the schema's name and type. project_id is inferable, but not explicitly documented.

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 opens with a clear statement of the resource ('Контекст проекта') and enumerates its contents: instructions, tasks, map table of contents, memory, files, and dialogs. It also explicitly contrasts itself with whats_new, making it easy for an agent to distinguish this tool from its siblings.

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 gives an explicit trigger condition: call once when taking on a project for the first time. It also names the alternative ('whats_new') for familiar projects and adds a cost signal ('он дешевле'), which is concrete, actionable guidance.

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