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

Annotations only declare readOnly/openWorld=false; the description adds real behavioral context beyond them: the output is 4–6 labelled directions each with a one-line pitch, it also surfaces the brief currently on file and whether it is a month old and due for review. It also discloses a generation constraint (Pith may draw a hand or a child, never a specific person, so needs-photos options must be framed as 'send photos' rather than a promise) — exactly the kind of limitation annotations cannot express. No contradiction with readOnlyHint, since the write step is delegated to set_brief.

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?

It is front-loaded with the purpose and every clause is load-bearing (sources, output shape, owner choice, set_brief handoff, needs-photos framing, return values). The single sprawling paragraph mixes instructions, content constraints and return-value facts without separation, which costs some scannability but not correctness.

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 does the work of explaining what comes back (directions, existing brief, review-due flag), and annotations cover the safety profile. The remaining gap is preconditions: it never says whether Instagram must be connected or a Brand DNA must exist before proposing, which matters given sources from 'the account's own Instagram'.

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% for both parameters, so the schema carries handle and the context/word-count rules on its own. The description only implicitly touches `handle` via 'the account's own Instagram' and says nothing about the mandatory context parameter, so it adds no meaning beyond the structured field.

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?

"4–6 directions for the daily posts, from the account's own Instagram, website and Brand DNA, each with one line on what Pith would make" is a concrete verb-plus-output statement, and it also notes the secondary return (current brief on file, review-due flag). What it does not do is distinguish itself from draft-generating siblings such as generate_draft — an agent could reasonably confuse 'directions Pith would post' with an actual draft.

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 states the workflow explicitly: generate options, show them to the owner as choices, let them pick several, then call set_brief with the chosen labels plus any free-form wording. That names the alternative/next tool and the condition that triggers it, and the needs-photos clause adds a specific presentation rule instead of leaving it to inference.

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