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

Well beyond the annotations: it discloses the side effect of marking the page as changed (bumping it to the top of fastero_list_pages), the 500-character truncation and empty-message refusal, the 5-error retention with fastero_update_page not clearing them, a 10-per-minute-per-person rate limit, and viewer-level permissions. The only slight gap is that it says the tool answers { ok: true } but doesn't say what the failure shape looks like beyond the 'Page not found' string.

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 with the core action and its consumer, then layered with constraints in descending importance. It is dense and long for a single paragraph, and 'The card calls it, and it is marked app-only' sits awkwardly next to the permission sentence later on, but nearly every clause carries non-redundant information.

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?

For a 3-parameter write tool with no output schema, the description covers the full contract: who calls it, side effects, message normalization, retention window, rate limit, authorization level, and the success/not-found responses. An agent has everything needed to call it correctly and to predict the consequences.

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 the baseline is a 3, but the description adds real meaning: the message is trimmed, capped at 500 characters, and refused when empty — normalization and validation rules absent from the schema. It also clarifies that pageId refers to a page that may have been deleted or belong to another project, which explains the error path.

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 precise verb and resource — saving an error thrown by a hosted page's own code — and anchors it against siblings by naming fastero_show_page (the card), fastero_get_page (where it lands), and fastero_list_pages (ordering effect). It also carves out what it is not for: 'not for reporting problems with Fastero itself.' An agent can distinguish this from every other write tool in the sibling list.

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?

Explicitly identifies the caller ('The card calls it, and it is marked app-only') and the exclusion (not for Fastero's own problems), which tells an agent both who invokes it and when it should stay away. It even names the downstream consumer — whoever fixes the page reads it in fastero_get_page's recentErrors — so the routing decision is unambiguous.

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