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

The description does real work here by disclosing what the call returns and that it opens/reuses the automatic session and 'notes when you looked' — behavior the annotations do not cover. However, that disclosed side effect (opening a session, recording a view event) conflicts with the declared readOnlyHint=true and, arguably, idempotentHint=true, so the two sources give the agent incompatible expectations about whether the call mutates state.

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 imperative ('CALL THIS FIRST'), then return contents, then fallback, then side effects — four compact clauses with no filler. Every sentence carries information an agent needs before calling.

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 properly enumerates the brief's contents so the agent knows what to expect, and it discloses side effects. It stops short of explaining how the size parameter changes depth or how the brief text is structured/sectioned for parsing.

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%, so all three parameters (size enum, folder, project name-or-id) are already documented, and the description's 'No project: lists projects' merely restates the schema. It adds nothing about what quick/standard/deep actually change in the returned brief, which is the one non-obvious 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?

States a specific action and resource ('Returns the brief as text') and enumerates exactly what the brief contains: hard rules, handoff note, review mode, conflicts, todos/claims, problems, recent changes, decisions, learnings. The fallback behavior ('No project: lists projects') is called out, and the sibling tools (manage_*, log_work, search) are clearly differentiated as write/query tools rather than the entry point.

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?

Gives an explicit trigger ('CALL THIS FIRST in every conversation about a project') and a variant path when no project is supplied. It does not name a competing tool to use instead of this one or state when an agent should skip it on repeat visits, so it falls short of full when/when-not coverage.

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