get_project_context

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

With no annotations, the description carries full transparency burden, and it discloses key behaviors: it reads three named sources, returns empty sections for new projects, and never returns the entire vault. The guarantee about new projects prevents the agent from misinterpreting missing output as an error. The only gap is what happens when the project argument is invalid or the files are absent, but that is not critical.

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?

Four short sentences present the outcome first, then sources, then edge-case behavior, then a boundary—all relevant and no filler. The line 'Never returns the entire vault' is especially compact and valuable.

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?

The description explains the read behavior and edge case effectively, and an output schema exists so return-structure details are not needed here. However, with three parameters and no schema descriptions, the complete absence of parameter documentation leaves the tool partially underspecified. An agent could call it correctly via defaults, but it would have to guess at the influence of recent_sessions and recent_decisions.

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 explain the three parameters. It mentions 'Project State.md' and 'newest session and decision notes,' which loosely maps to project and the count parameters, but never states that recent_sessions and recent_decisions control how many notes are read, nor what format project takes. The parameter names are partially self-explanatory, but the description adds no meaningful parameter guidance.

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 'Retrieve concise durable memory before substantial work,' a specific verb/object pair with a clear trigger condition. It goes on to name the exact sources (Project State.md, newest session and decision notes) and states what it will not do ('Never returns the entire vault'), which separates it from read_note and search_memory.

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 phrase 'before substantial work' supplies an explicit when-to-use signal, positioning the tool as the starting point for context gathering. It does not explicitly name alternatives or exclusions, but the boundary 'Never returns the entire vault' gives agents a cue that this is not a vault-wide read. A stronger definition would name search_memory or read_note as alternatives for broader or note-specific reads.

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