project_view

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real context by disclosing that the same read can target three quite different sources (a tracked research project, a gene-archive site folder, a .ged file), but it largely restates the what enum and says nothing about empty results, error behavior, or size limits on the tree checks.

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?

Two sentences of reasonable length, with the session-start rule placed last so it is easy to miss. The opening sentence is a tangled em-dash chain with an embedded parenthetical list that is hard to parse on first read; the mode/return-value mapping would be far clearer as a short list.

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 return values need not be spelled out, and annotations handle the safety profile; the description covers source selection, the primary entry point, and most modes. The remaining gap is coverage of the 'workflow' and 'resources' modes and the 'lang' parameter, which leaves an agent guessing about two of seven behaviors.

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 60%, and the description compensates partially: it maps 'summary' to concrete contents (people, open leads, recent searches, problems) and 'record' to family and sources, which adds meaning beyond the enum. However it silently omits the 'workflow' and 'resources' enum values and never mentions the 'lang' parameter, so two documented gaps remain for a 5-parameter dispatcher.

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 names a specific verb (read) and enumerates what is read: project summary, a single record with family and sources, a text search, the search log, and tree checks. It is distinguishable from project_save and project_transfer, though it overlaps noticeably with the sibling project_log (it exposes a 'log' mode) without acknowledging that overlap.

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?

There is one explicit directive — "Start every session on an existing project with what='summary'" — which is genuinely useful. Beyond that, nothing tells the agent when to pick this tool over project_log, project_coverage, project_evidence, or audit_tree, nor when the record/search/checks modes are preferable to those siblings.

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