pob_render_image

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

Beyond the readOnly/destructive=false annotations, it discloses real behavior: the tree is drawn by the original Lua PassiveTreeView with PoB textures/frames/backgrounds/arcs, zoom scales everything together, showLabels is off by default, class-ascendancy links are hidden, and the image is returned inline in MCP. That is substantive context the annotations cannot provide; only the exact return payload shape is left implicit.

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?

The most decision-relevant statement (create a PNG of the build plus the view list) is front-loaded, and each following sentence adds new information rather than repeating the name. It is dense and slightly run-on, and the phrase "смотрите pages" is a little cryptic, but there is no filler.

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 9-parameter, no-output-schema rendering tool with zero annotation-level parameter documentation, the description supplies enough to call it correctly: view taxonomy, id prerequisite, treeScope, query, zoom, labels and paging. Missing width/height guidance and a note on what the returned image dimensions/format look like keep it from full completeness.

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 0%, so the description must carry the parameter burden and largely does: it explains view options, zoom, showLabels default, treeScope values (allocated/full), query (filters text or selects a tree region), page, and id for node/item. Only width and height are undocumented, which is a minor residual gap for a 9-parameter tool.

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 a concrete verb+resource in Russian ("Создать PNG сборки") and enumerates the renderable views (сводка, дерево, характеристики, камни, предметы, условия, заметки, предупреждения, полный отчёт), so the agent knows exactly what the tool produces. It never names a sibling like pob_get_tree or pob_node_tooltip to distinguish the PNG render from the JSON/text tree tools, so it stops short of a 5.

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 gives a useful prerequisite ("Для node/item нужен id из каталога/отчёта") and notes pagination for long sections, which steers correct invocation. However, it never says when to choose this over the sibling tree/inspect tools, nor any exclusions, so usage is only implied.

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