Project Context Tool

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

With no annotations, the description carries full burden and does substantial work: it discloses the delta behavior ('with what changed since you last read it') and the no-document fallback returning cemainou/next_steps material. It omits what happens on an invalid repo/session value and does not state that reading apparently records a per-user read marker, which is an implicit side effect.

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?

Purpose and read-before-working guidance are front-loaded, and the write-path pointer comes last. The middle enumeration of document contents is long but is load-bearing, telling the agent what the returned reference covers.

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?

No output schema exists, and the description compensates by describing the return: the context document plus a change-since-last-read summary, or seed material when none exists. That plus the save_context pointer is everything needed to call and interpret it.

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 100%, so repo, project, and session are already documented including the precedence rule ('session wins over repo'). The description adds nothing about them, so the baseline of 3 applies.

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?

Specific verb ('read'/'returns') plus a precisely identified resource: the project's context document at /ctx, enumerated by what it contains. It separates itself from save_context by naming that sibling as the writer, but leaves overlap with project_brief and read_document unaddressed.

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?

'The lasting reference to read before working on it' gives a clear trigger condition (start of work on a project). It names save_context as the alternative for the write path and explains the fallback when no document exists, but never states when to prefer project_brief or read_document instead.

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